© 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. 98802
    Prev
    Next
    INDEX
    Explanations

    Massachusetts

    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
    ä¸īçĤ¹
    -0.31
    ä¸Ģæľµ
    -0.28
    weise
    -0.28
    tz
    -0.27
     wag
    -0.26
    arend
    -0.26
    xl
    -0.25
    ocz
    -0.24
    æѦæ±ī
    -0.24
    affle
    -0.24
    POSITIVE LOGITS
    ç¬ı
    0.33
    sites
    0.26
    ominated
    0.26
    desc
    0.26
    earn
    0.24
    assin
    0.24
    åŃIJåŃĻ
    0.24
    atives
    0.24
     dynasty
    0.23
    æĹ¥è®¯
    0.23
    Activations Density 0.053%

    No Known Activations