© 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. 40155
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Sundays
    -0.25
    elem
    -0.25
    INCLUDING
    -0.25
    problems
    -0.24
    è¡¡
    -0.23
     boys
    -0.23
     Elementary
    -0.23
    奴
    -0.23
    ::
    -0.23
    å£
    -0.23
    POSITIVE LOGITS
    awy
    0.29
    $__
    0.28
    wis
    0.26
    年以æĿ¥
    0.24
    richt
    0.24
    åıijå±ķä¸Ń
    0.23
    ypo
    0.23
     honda
    0.23
    .skin
    0.23
    åĺĺ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.