© 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. 27-TRANSCODER-HP
    7. 9222
    Prev
    Next
    INDEX
    Explanations

    Languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aper
    -0.27
    å±ķåĵģ
    -0.25
     gere
    -0.25
     minority
    -0.23
    ionate
    -0.23
    yal
    -0.23
    ÅĪ
    -0.23
    avage
    -0.23
    DF
    -0.23
    ner
    -0.23
    POSITIVE LOGITS
    æ±īæĹı
    0.52
     English
    0.45
     Western
    0.43
    English
    0.42
    西æĸ¹
    0.41
    èĭ±æĸĩ
    0.41
    èĭ±è¯Ń
    0.39
    欧ç¾İ
    0.39
     cartesian
    0.38
    西æ´ĭ
    0.38
    Activations Density 0.006%

    No Known Activations