© 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. 7-RESID-POST-AA
    11. 76293
    Prev
    Next
    INDEX
    Explanations

    haired

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    挎
    -0.07
    ƫ
    -0.07
    响应
    -0.06
    保证
    -0.06
    ically
    -0.06
    NJ
    -0.06
    越过
    -0.06
    ﳊ
    -0.06
    ulatory
    -0.06
     Standard
    -0.06
    POSITIVE LOGITS
     движ
    0.07
     cena
    0.07
     paperwork
    0.07
     "\""
    0.07
     mudança
    0.07
    퇼
    0.07
     Creed
    0.07
     Clark
    0.06
     процедур
    0.06
    더
    0.06
    Activations Density 0.006%

    No Known Activations