© 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. 31-TRANSCODER-HP
    7. 19227
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marvin
    -0.27
    åľ¨æľªæĿ¥
    -0.27
     in
    -0.26
    ***/↵↵
    -0.26
     today
    -0.25
     circa
    -0.24
    ähr
    -0.24
    ervices
    -0.24
    .localtime
    -0.24
    æĹ¢
    -0.24
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.31
    å°±æĺ¯
    0.31
    utter
    0.30
    è¿Ļæīįæĺ¯
    0.28
    æīįæĺ¯
    0.27
    ê¼´
    0.27
    å°±æĺ¯è¦ģ
    0.27
    åŀ£
    0.26
    å°±æĺ¯åľ¨
    0.25
    å°±æĺ¯ä¸Ģ个
    0.25
    Activations Density 0.161%

    No Known Activations