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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8873
    Prev
    Next
    INDEX
    Explanations

    Generated code, "DO NOT EDIT"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unidentified
    -0.27
    ARN
    -0.26
    .si
    -0.26
    arn
    -0.26
    itizen
    -0.24
    ays
    -0.24
    eof
    -0.24
     Strauss
    -0.23
     anonymously
    -0.23
    åijĹ
    -0.23
    POSITIVE LOGITS
    ä¸įåºĶ
    1.02
     shouldn
    0.93
    ä¸įåºĶ该
    0.93
    ä¸įå¾Ĺ
    0.85
    ä¸įå®ľ
    0.80
    ä¸įåħģ许
    0.76
    严ç¦ģ
    0.73
    ä¸įèĥ½
    0.73
    ç¦ģæŃ¢
    0.70
    ä¸į该
    0.69
    Activations Density 0.006%

    No Known Activations