© 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. 24-TRANSCODER-HP
    7. 149387
    Prev
    Next
    INDEX
    Explanations

    Foreign characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ§İ
    -0.31
    pee
    -0.25
    redicate
    -0.24
    åħ¬ç«ĭ
    -0.24
    itung
    -0.23
    ä½Ĩå®ĥ
    -0.23
    singular
    -0.23
    alte
    -0.22
    ulses
    -0.22
    aub
    -0.22
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½æĺ¯
    0.33
    è¿ĻäºĽ
    0.32
    è¿ĻäºĽéĹ®é¢ĺ
    0.30
    è¿ĻäºĽä¸ľè¥¿
    0.29
    éĢĻäºĽ
    0.28
    æį¨
    0.27
    “These
    0.27
     these
    0.27
    ãģĵãĤĮãĤīãģ®
    0.26
    These
    0.26
    Activations Density 0.966%

    No Known Activations