© 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. 39559
    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
    ',...↵
    -0.28
    å¸Ńåį·
    -0.25
    æµ·æ¹¾
    -0.24
     Ðļо
    -0.24
    teil
    -0.24
    管çIJĨæĿ¡ä¾ĭ
    -0.24
    éģĴ
    -0.24
     ayr
    -0.23
    FRING
    -0.23
     tiers
    -0.23
    POSITIVE LOGITS
    8
    0.31
    9
    0.29
    4
    0.28
    .
    0.28
    5
    0.27
     White
    0.27
    3
    0.27
    6
    0.27
    ãĢĤ
    0.26
    ||
    0.26
    Activations Density 0.434%

    No Known Activations

    This feature has no known activations.