© 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. 40398
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and acronyms

    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
    иде
    -0.26
    åĽłä¸ºåľ¨
    -0.25
    FIN
    -0.25
    ADE
    -0.25
    iete
    -0.25
     spre
    -0.25
    ç±³åħ°
    -0.25
    IDL
    -0.25
    iena
    -0.25
    éģĤ
    -0.24
    POSITIVE LOGITS
    ccc
    0.29
     Om
    0.28
    kar
    0.28
    ttl
    0.27
    cop
    0.27
    cccc
    0.27
    urv
    0.27
    cac
    0.27
    ccb
    0.27
    ll
    0.26
    Activations Density 0.024%

    No Known Activations