© 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. 64159
    Prev
    Next
    INDEX
    Explanations

    State

    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
    SEX
    -0.28
     Specs
    -0.26
    ervlet
    -0.25
    createClass
    -0.25
    ilos
    -0.25
    urv
    -0.24
    dater
    -0.24
    çŃīå·¥ä½ľ
    -0.24
    ,i
    -0.23
     полÑĥ
    -0.23
    POSITIVE LOGITS
    dia
    0.27
    0.26
    core
    0.25
     unc
    0.25
     coast
    0.24
     wh
    0.24
     homo
    0.24
    ÙĦØ©
    0.24
    ç´§å¼ł
    0.23
    1
    0.23
    Activations Density 2.506%

    No Known Activations