© 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. 87316
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    ·¨
    -0.31
    éĤ£ç§į
    -0.29
    åĩºäºĨ
    -0.28
    åĩºæĿ¥çļĦ
    -0.26
    éĿł
    -0.26
     reconcile
    -0.26
    iaux
    -0.26
    æĿ¥çļĦ
    -0.26
    ali
    -0.25
    éli
    -0.25
    POSITIVE LOGITS
    fat
    0.32
     fat
    0.28
     doub
    0.27
    weit
    0.26
     Nationwide
    0.24
    ieves
    0.24
     tomorrow
    0.24
     vac
    0.24
     Tonight
    0.24
    jt
    0.24
    Activations Density 0.029%

    No Known Activations