© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40629
    Prev
    Next
    INDEX
    Explanations

    car

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
     Scenario
    -0.26
    çķĮ
    -0.26
     Bound
    -0.25
     origin
    -0.25
     Rider
    -0.25
    èµ·æºIJ
    -0.25
    çļĦä¸ĸçķĮ
    -0.24
    Bound
    -0.24
     HQ
    -0.24
     Eid
    -0.24
    POSITIVE LOGITS
    etti
    0.30
    cor
    0.30
    ekt
    0.30
    inate
    0.28
    ini
    0.28
    plen
    0.27
    obb
    0.27
     rectangular
    0.26
    so
    0.26
    iscal
    0.25
    Activations Density 26.203%

    No Known Activations