© 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. 31-TRANSCODER-HP
    7. 19140
    Prev
    Next
    INDEX
    Explanations

    movement verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -mort
    -0.28
    -fit
    -0.26
    atel
    -0.26
    åħīåѦ
    -0.25
    decl
    -0.25
    posted
    -0.25
     MULT
    -0.25
     Icons
    -0.24
    fits
    -0.24
     telephone
    -0.24
    POSITIVE LOGITS
     picking
    0.32
     pushing
    0.31
     picks
    0.31
     moving
    0.31
    gü
    0.30
     flowing
    0.29
     bringing
    0.29
     PUSH
    0.28
     pom
    0.28
     pat
    0.28
    Activations Density 1.308%

    No Known Activations