© 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. 9-TRANSCODER-HP
    7. 29725
    Prev
    Next
    INDEX
    Explanations

    ymous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĩ
    -0.25
    æĸ¼
    -0.25
    æ°ijäºĭ
    -0.24
    ,Th
    -0.24
    orraine
    -0.24
     è¾ĵåħ¥
    -0.24
    åĨĻä¸ĭ
    -0.23
    -Th
    -0.23
    Stored
    -0.23
    PHA
    -0.23
    POSITIVE LOGITS
    Course
    0.28
    alyze
    0.28
     ride
    0.27
    stile
    0.26
    ç³»
    0.25
    Voice
    0.25
     hottest
    0.25
     TOD
    0.25
    tram
    0.25
     Neighborhood
    0.25
    Activations Density 0.811%

    No Known Activations