Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 202
    Prev
    Next
    INDEX
    Explanations

    prime factors and remainders

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (texture
    -0.07
    tures
    -0.06
    ㊥
    -0.06
    =title
    -0.06
     contentView
    -0.06
    نقص
    -0.06
     pstmt
    -0.06
    riger
    -0.06
    公元
    -0.06
    leon
    -0.06
    POSITIVE LOGITS
    abis
    0.08
     lệnh
    0.07
     Package
    0.07
    開展
    0.07
    解决
    0.07
     aplic
    0.07
    Bounding
    0.07
     halt
    0.07
    _vector
    0.07
    检
    0.07
    Activations Density 0.009%

    No Known Activations