© 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. 24-TRANSCODER-HP
    7. 149575
    Prev
    Next
    INDEX
    Explanations

    foreign writings or 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
    Not in Any Lists

    No Comments

    Negative Logits
    æĬij
    -0.30
    pick
    -0.29
     n
    -0.27
    ery
    -0.27
    imum
    -0.24
    mine
    -0.24
    é¦ĸéĢī
    -0.23
    e
    -0.23
    ne
    -0.23
     ))
    -0.23
    POSITIVE LOGITS
    ç»ĵæĿŁ
    0.78
    ç»ĵæĿŁäºĨ
    0.67
    éĢĢåĩº
    0.61
    ç»ĵæĿŁåIJİ
    0.60
    çµIJæĿŁ
    0.59
    离åİ»
    0.59
     exit
    0.56
    离å¼Ģ
    0.55
     ending
    0.55
    å®Įç»ĵ
    0.54
    Activations Density 0.931%

    No Known Activations