© 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. 150600
    Prev
    Next
    INDEX
    Explanations

    Describing creative works

    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
    ä¹ĭä¸Ģ
    -0.27
    Ix
    -0.26
    æľ
    -0.26
    绾
    -0.25
    åĩºè·¯
    -0.25
    缦
    -0.25
    ä»ĭ
    -0.24
    trait
    -0.24
    wald
    -0.24
    åĨĮ
    -0.24
    POSITIVE LOGITS
     appeal
    0.28
     appeals
    0.28
    blast
    0.27
    趣
    0.25
    é¢ĺæĿIJ
    0.25
     Appeal
    0.25
    .GetItem
    0.25
     Hugo
    0.24
    Marvel
    0.24
    ç¨ĭå¼ı
    0.23
    Activations Density 0.150%

    No Known Activations