© 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. 33-TRANSCODER-HP
    7. 53737
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alli
    -0.30
    èħ®
    -0.29
    ç©¿
    -0.28
    æİī
    -0.27
    åĬŁåĬ³
    -0.26
    ej
    -0.25
    ijd
    -0.25
    ħį
    -0.25
    stype
    -0.25
    enu
    -0.25
    POSITIVE LOGITS
     Budd
    0.26
     term
    0.25
     Osman
    0.25
    erd
    0.25
    &utm
    0.25
     Term
    0.24
     mù
    0.24
    UTE
    0.24
     Prices
    0.23
    .term
    0.23
    Activations Density 0.019%

    No Known Activations