© 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. 40228
    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
    olution
    -0.26
    åĽŀ头
    -0.26
     POSIX
    -0.24
    {"
    -0.24
     puls
    -0.23
     inne
    -0.23
    {'
    -0.23
    ,{"
    -0.23
     hospitality
    -0.23
    æµĭ
    -0.23
    POSITIVE LOGITS
    åľĪ
    0.28
    æĸ«
    0.27
    ampp
    0.25
     اÙĦÙĪا
    0.25
     getField
    0.25
    plemented
    0.24
    ält
    0.23
     journal
    0.23
     SPL
    0.23
    ators
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.