© 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. 40286
    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
    attle
    -0.28
    çĹħæ¯ĴæĦŁæŁĵ
    -0.27
    ç£ķ
    -0.26
    .refs
    -0.25
    Fel
    -0.25
    changed
    -0.25
    Recovered
    -0.25
    elta
    -0.25
    Separated
    -0.25
    -Sep
    -0.24
    POSITIVE LOGITS
     necessary
    0.31
    æŀ¶åŃIJ
    0.29
     lie
    0.29
     (
    0.29
     simpl
    0.28
     absolute
    0.28
     graph
    0.28
     full
    0.27
    åIJĥ饱
    0.27
     leading
    0.27
    Activations Density 16.573%

    No Known Activations

    This feature has no known activations.