© 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. 8490
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    \",\
    -0.28
    !),
    -0.28
    âĢ¦)
    -0.27
    Moder
    -0.26
    好好
    -0.25
    OwnerId
    -0.25
    æĻ¤
    -0.25
    ...",
    -0.24
    æĬ±åĽ¢
    -0.23
    ."),
    -0.23
    POSITIVE LOGITS
    ï¼Ł↵
    0.56
    .↵
    0.53
    ?↵
    0.51
    ãĢĤ↵
    0.51
    ï¼ļ↵
    0.49
     .↵
    0.49
    :↵
    0.48
     ?↵
    0.44
    ---↵
    0.42
    ï¼Ľ↵
    0.41
    Activations Density 0.016%

    No Known Activations