© 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. 22-TRANSCODER-HP
    7. 111346
    Prev
    Next
    INDEX
    Explanations

    Groups or classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     storms
    -0.26
    storms
    -0.26
    aje
    -0.26
    çIJĨæĢ§
    -0.25
     weighing
    -0.25
    ä¸Ģå¹ķ
    -0.23
    éļ§
    -0.23
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.23
    partial
    -0.23
    張貼
    -0.23
    POSITIVE LOGITS
     participants
    0.29
    ìļ´
    0.29
     offerings
    0.27
     offered
    0.26
     versa
    0.26
    线ä¸Ĭ
    0.26
    jos
    0.25
    vec
    0.25
    åĬŀ
    0.25
     Offer
    0.25
    Activations Density 0.037%

    No Known Activations