© 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. 40070
    Prev
    Next
    INDEX
    Explanations

    D

    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
    -mouth
    -0.27
    æĹºçĽĽ
    -0.26
    wins
    -0.26
    -moving
    -0.25
    ermen
    -0.25
    è§ĦèĮĥåĮĸ
    -0.24
    ç§ģ
    -0.24
    _VOLT
    -0.23
     Missing
    -0.23
    .ini
    -0.23
    POSITIVE LOGITS
    subst
    0.29
    è´Ń
    0.27
     subparagraph
    0.26
    çļĦåĽłç´ł
    0.26
    æŃ£åľ¨è¿Ľè¡Į
    0.25
    irs
    0.24
    ETY
    0.24
    åħ¨
    0.24
    ilde
    0.24
    lli
    0.24
    Activations Density 0.042%

    No Known Activations