© 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. 151299
    Prev
    Next
    INDEX
    Explanations

    will

    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
    acy
    -0.28
    ibly
    -0.28
     ru
    -0.27
    ynos
    -0.27
    缮æłĩä»»åĬ¡
    -0.26
    OGLE
    -0.25
    å¤ļæł·åĮĸ
    -0.24
    jectives
    -0.24
    ru
    -0.24
    ãģĿãģĨãģ§
    -0.24
    POSITIVE LOGITS
    ä¼ļ被
    0.39
    will
    0.30
     will
    0.29
    æĪij们ä¼ļ
    0.28
    Will
    0.27
    ä¼ļåľ¨
    0.27
    symbol
    0.26
    ä¼ļ
    0.26
    ek
    0.26
    coding
    0.26
    Activations Density 0.243%

    No Known Activations