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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129321
    Prev
    Next
    INDEX
    Explanations

    Kuwait

    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_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
    ledged
    -0.08
     Implemented
    -0.08
    他知道
    -0.08
     Estate
    -0.07
    小麦
    -0.07
    ㋯
    -0.07
    焊
    -0.07
    淌
    -0.07
    Constructed
    -0.07
     Generally
    -0.07
    POSITIVE LOGITS
     Kuwait
    0.08
     Ku
    0.07
    こんに
    0.07
    cccc
    0.07
    .mybatis
    0.07
     التابعة
    0.07
    白领
    0.07
    豢
    0.07
    ulum
    0.07
    𝕺
    0.07
    Activations Density 0.004%

    No Known Activations