© 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. 149456
    Prev
    Next
    INDEX
    Explanations

    adverbs of degree

    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
    æ¯Ķå¦Ĥ
    -0.32
    ä¾ĭå¦Ĥ
    -0.31
    æĬĵ
    -0.29
    æ¯Ķå¦Ĥ说
    -0.27
     there
    -0.25
    çľĭçĿĢ
    -0.25
     look
    -0.25
     Look
    -0.25
    åĮħæĭ¬
    -0.24
    cht
    -0.24
    POSITIVE LOGITS
    .used
    0.29
     Crimes
    0.27
    åİĿ
    0.26
     foll
    0.25
    tas
    0.24
     msgs
    0.24
    éĻ©
    0.24
    endra
    0.23
    tog
    0.23
    åĽłæŀľ
    0.23
    Activations Density 0.112%

    No Known Activations