© 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. 39743
    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
     '..
    -0.26
     appropriated
    -0.24
    ä¸ĭæīĭ
    -0.24
    leitung
    -0.24
    åĿĢ
    -0.23
    mage
    -0.23
    -paying
    -0.23
    gings
    -0.23
    æµ·æĬ¥
    -0.23
    åįģåŃĹ
    -0.23
    POSITIVE LOGITS
     Enabled
    0.26
     senses
    0.26
    .getResources
    0.25
    Touches
    0.25
    NEL
    0.25
    -roll
    0.24
    loses
    0.24
    olia
    0.24
    ync
    0.24
    .ToList
    0.24
    Activations Density 0.069%

    No Known Activations

    This feature has no known activations.