© 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. 112321
    Prev
    Next
    INDEX
    Explanations

    ination

    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
    ged
    -0.30
    æĸ°åŁİ
    -0.29
    svp
    -0.29
    æ¼Ķ
    -0.27
    éĩį
    -0.26
     Тем
    -0.25
    ì§Ħ
    -0.25
    ÃŃcul
    -0.24
     ghost
    -0.24
    ting
    -0.24
    POSITIVE LOGITS
     rightly
    0.29
    æĸ¹å¼ıè¿Ľè¡Į
    0.28
    èĢĮåĩº
    0.27
    è¦ģ好好
    0.26
    ount
    0.26
     feas
    0.25
    oland
    0.24
    ç±³ç²ī
    0.24
    榷
    0.24
    outu
    0.24
    Activations Density 0.102%

    No Known Activations