© 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. 30-TRANSCODER-HP
    7. 96038
    Prev
    Next
    INDEX
    Explanations

    Instead

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĭãģ®ãģ¯
    -0.27
    eworld
    -0.26
    篮æĿ¿
    -0.26
    åľ»
    -0.25
    让æĤ¨
    -0.24
    ä½ĵçİ°åľ¨
    -0.24
    æīįè¡Į
    -0.24
    ascade
    -0.24
    valuate
    -0.24
    åĨį说
    -0.24
    POSITIVE LOGITS
     of
    0.69
    of
    0.54
     của
    0.50
     Of
    0.47
    _of
    0.47
    .of
    0.44
    ,
    0.44
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.43
    Of
    0.41
    	of
    0.41
    Activations Density 0.023%

    No Known Activations