© 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. 87941
    Prev
    Next
    INDEX
    Explanations

    Numbers two and three

    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
    详
    -0.28
    éĽ¾
    -0.26
     Py
    -0.24
    px
    -0.24
    ker
    -0.24
     diss
    -0.24
    elle
    -0.24
    escaping
    -0.24
    ({_
    -0.24
     statistic
    -0.24
    POSITIVE LOGITS
     dozen
    0.26
    ä¸ŃçļĦ
    0.24
    licht
    0.24
     legitimately
    0.24
    .Request
    0.24
     forever
    0.24
    ulner
    0.24
    visible
    0.24
     easily
    0.23
    æĸ
    0.23
    Activations Density 0.012%

    No Known Activations