© 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. 129495
    Prev
    Next
    INDEX
    Explanations

    Diverse document sources

    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
    weise
    -0.32
     firstly
    -0.31
    ha
    -0.31
    remen
    -0.31
    _cls
    -0.29
     yuan
    -0.29
    hores
    -0.28
    _SMS
    -0.27
     Qing
    -0.27
     Firstly
    -0.26
    POSITIVE LOGITS
     Glo
    0.27
    ”—
    0.26
    —or
    0.25
    Ằ
    0.25
     bicy
    0.24
    âĺIJ
    0.24
    :>
    0.24
     unsus
    0.23
    —for
    0.23
     stub
    0.23
    Activations Density 80.655%

    No Known Activations