© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 110940
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Negative Logits
    ieux
    -0.28
    antan
    -0.27
    æķĪ
    -0.26
    ãģĹãĤĩãģĨ
    -0.26
    piring
    -0.26
     strengths
    -0.24
    æĬ¤èĤ¤
    -0.24
    ören
    -0.24
    precated
    -0.23
    ढ
    -0.23
    POSITIVE LOGITS
    å¾Īå¤ļ
    0.32
    è¿Ļä¹Īåģļ
    0.32
    æĹ©åľ¨
    0.29
    è¿Ļæł·åģļ
    0.29
    è¿Ļä½į
    0.26
    媾
    0.24
    该åİ¿
    0.24
    esco
    0.24
     *_
    0.24
    вол
    0.24
    Activations Density 0.001%

    No Known Activations