© 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. 87402
    Prev
    Next
    INDEX
    Explanations

    code, and/or, agreements

    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
     avis
    -0.28
    Ùĭ
    -0.28
    ager
    -0.26
    หà¸Ļ
    -0.24
    aling
    -0.23
    毯
    -0.23
     اÙĦعÙħ
    -0.23
    æ¯ĶæĪij
    -0.23
    urious
    -0.22
    æ¯ĶåĪĨ
    -0.22
    POSITIVE LOGITS
    æĿ¥è¿Ľè¡Į
    0.30
    çĶ¨äºİ
    0.29
    äºİ
    0.26
    æĿ¥åģļ
    0.26
    以便
    0.25
    åı¯çĶ¨äºİ
    0.25
    IRECT
    0.25
    åİ»åģļ
    0.24
    æĸ¼
    0.24
    å°±æĬĬ
    0.24
    Activations Density 0.007%

    No Known Activations