© 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. 39004
    Prev
    Next
    INDEX
    Explanations

    mar

    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
    Mar
    -0.43
     mar
    -0.42
    MAR
    -0.40
    mar
    -0.39
    _mar
    -0.37
    .mar
    -0.37
     Mar
    -0.34
    -mar
    -0.33
    .Mar
    -0.32
     Marcel
    -0.31
    POSITIVE LOGITS
    atto
    0.31
    ulin
    0.31
    ł
    0.30
    athon
    0.29
     anthropology
    0.26
    teenth
    0.26
    Ulus
    0.26
    dra
    0.26
    atan
    0.26
     tat
    0.26
    Activations Density 10.056%

    No Known Activations