© 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. 87935
    Prev
    Next
    INDEX
    Explanations

    title

    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
    otics
    -0.30
    ä¸īæĸ¹
    -0.27
    <!--↵
    -0.27
    ç½
    -0.26
    æľŃ
    -0.25
     characterize
    -0.25
    antine
    -0.25
    jähr
    -0.25
     Pvt
    -0.24
    á»ĩn
    -0.24
    POSITIVE LOGITS
    çļĦ第ä¸Ģ个
    0.28
    è¥¿çº¢æŁ¿
    0.27
    é¦Ĵ头
    0.27
     prefix
    0.26
    tems
    0.25
    éĴł
    0.24
    *&
    0.24
    .prefix
    0.23
     Store
    0.23
    urch
    0.23
    Activations Density 0.000%

    No Known Activations