© 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. 96149
    Prev
    Next
    INDEX
    Explanations

    or

    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
     shorter
    -0.37
     cheaper
    -0.36
     simpler
    -0.35
     narrower
    -0.35
     smaller
    -0.35
     softer
    -0.35
    æĽ´å¼º
    -0.32
     richer
    -0.32
    arser
    -0.32
    è·ijåİ»
    -0.32
    POSITIVE LOGITS
    থ
    0.28
    itu
    0.26
    FontAwesome
    0.26
    å¾ĹåĪĨ
    0.26
    ilen
    0.25
    LE
    0.25
    éĿ¢
    0.25
    кÑĥÑĢ
    0.25
    cum
    0.24
    atts
    0.24
    Activations Density 0.003%

    No Known Activations