© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 128226
    Prev
    Next
    INDEX
    Explanations

    Instructions/advice

    np_max-act · gemini-2.0-flash

    sentences that give cautions, safety warnings, or recommendations (advising caution or suggesting professional help).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     london
    -0.07
    的地方
    -0.07
    (blocks
    -0.07
     dump
    -0.07
     knit
    -0.07
     Tây
    -0.07
    ESIS
    -0.07
     Logging
    -0.07
    故乡
    -0.07
     synchronize
    -0.07
    POSITIVE LOGITS
    雊
    0.07
    売れ
    0.06
    说过
    0.06
     marque
    0.06
    ropp
    0.06
    你知道
    0.06
    RefCount
    0.06
    альн
    0.06
    .accessToken
    0.06
    Vtbl
    0.06
    Activations Density 0.143%

    No Known Activations