© 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. 88603
    Prev
    Next
    INDEX
    Explanations

    Internet articles

    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
    pline
    -0.29
    ä¸īæĿ¡
    -0.29
    两æĿ¡
    -0.28
    第ä¸ĢæĿ¡
    -0.28
    ä¸Ģ级
    -0.27
    两级
    -0.26
    åįģæĿ¡
    -0.26
    øj
    -0.25
    pher
    -0.24
    ç¥ĸ
    -0.24
    POSITIVE LOGITS
    iveness
    0.29
     research
    0.24
    apy
    0.24
    inate
    0.24
    animate
    0.24
    posix
    0.24
    locator
    0.24
    -ves
    0.23
    les
    0.23
    interactive
    0.23
    Activations Density 0.001%

    No Known Activations