© 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. 35-TRANSCODER-HP
    7. 39731
    Prev
    Next
    INDEX
    Explanations

    iate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    modified
    -0.26
     modifications
    -0.26
    holders
    -0.25
    contracts
    -0.25
    -your
    -0.25
    sville
    -0.25
    flows
    -0.25
    æīĵå¾Ĺ
    -0.25
    vez
    -0.24
    ç»ĵæŀĦè°ĥæķ´
    -0.24
    POSITIVE LOGITS
    iator
    0.37
    inel
    0.34
    iate
    0.33
    iali
    0.31
    iant
    0.30
    uell
    0.30
    iates
    0.29
    ierte
    0.29
    iel
    0.29
    iere
    0.29
    Activations Density 2.609%

    No Known Activations