© 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. 39860
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     regions
    -0.74
     parts
    -0.70
     places
    -0.68
    éĥ¨ä½į
    -0.67
     place
    -0.62
     region
    -0.57
    åľ°æĸ¹
    -0.56
     areas
    -0.56
    çļĦåľ°æĸ¹
    -0.55
    regions
    -0.54
    POSITIVE LOGITS
     Serif
    0.28
     Sunderland
    0.27
     Redskins
    0.27
    å°ıäºĭ
    0.26
     Padres
    0.26
     Lauderdale
    0.25
     Broncos
    0.25
    èĢģå¸Ī们
    0.24
    .Tasks
    0.24
     Hurricanes
    0.24
    Activations Density 14.230%

    No Known Activations