© 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. 40203
    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
    alendar
    -0.27
    ÑĩÑijÑĤ
    -0.26
    å¬Ľ
    -0.26
    æĢİä¹Īåģļ
    -0.26
     ve
    -0.26
    è§Ĥæij©
    -0.25
    ä»Ģä¹ĪæŶåĢĻ
    -0.24
    çIJĨ念
    -0.23
    ENV
    -0.23
    _REPEAT
    -0.23
    POSITIVE LOGITS
    cies
    0.26
     urgently
    0.26
     skins
    0.25
    æľªæĿ¥
    0.24
    cop
    0.24
     convers
    0.24
    tridge
    0.24
    enity
    0.24
     complimentary
    0.24
    øre
    0.24
    Activations Density 2.303%

    No Known Activations

    This feature has no known activations.