© 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. 20-TRANSCODER-HP
    7. 63211
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pulls
    -0.28
     repeats
    -0.27
    æĭ©
    -0.26
    .pem
    -0.25
    uger
    -0.25
    quarter
    -0.25
    æݬ
    -0.25
     Quarter
    -0.24
     compte
    -0.24
    顧
    -0.23
    POSITIVE LOGITS
    èIJ½
    0.30
    draft
    0.29
    eed
    0.29
     UIB
    0.28
    unities
    0.27
    ------+------+
    0.26
    ez
    0.26
    гин
    0.25
    UIFont
    0.25
    eid
    0.25
    Activations Density 16.846%

    No Known Activations