© 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. 33-TRANSCODER-HP
    7. 52989
    Prev
    Next
    INDEX
    Explanations

    food, meat, and seafood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    诺
    -0.31
    ND
    -0.27
     ND
    -0.27
    ôi
    -0.26
    諾
    -0.26
    ë³´
    -0.26
    au
    -0.26
    _nd
    -0.26
    ASI
    -0.26
    åļı
    -0.26
    POSITIVE LOGITS
    æĹ©å°±
    0.26
    沸èħ¾
    0.26
    warts
    0.25
    äºĴåĪ©
    0.24
     amph
    0.24
    é£ŀç¿Ķ
    0.24
    éļį
    0.24
     pronounce
    0.24
    è¿ĻäºĽéĹ®é¢ĺ
    0.24
    _imp
    0.24
    Activations Density 0.011%

    No Known Activations