© 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. 30062
    Prev
    Next
    INDEX
    Explanations

    enzyme

    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
     caught
    -0.29
    é²Ł
    -0.28
    çIJIJ
    -0.27
    代
    -0.27
     elasticity
    -0.26
    第ä¸Ģä½į
    -0.26
     зло
    -0.25
    utation
    -0.24
     ||=
    -0.24
    ç»ĵåIJĪèµ·æĿ¥
    -0.24
    POSITIVE LOGITS
    ecd
    0.28
    inea
    0.28
    å¦Ĵ
    0.27
     Pul
    0.25
    ocal
    0.25
    iphy
    0.25
    çļĦéģĵçIJĨ
    0.24
     washington
    0.24
    飫
    0.23
     food
    0.23
    Activations Density 1.093%

    No Known Activations