© 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. 150266
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     chóng
    -0.31
    anel
    -0.29
    å°±æĺ¯ä¸ºäºĨ
    -0.29
     tắc
    -0.29
    æŃ¤äºº
    -0.28
    骶
    -0.27
     ren
    -0.26
    çļĦä¿¡å¿ĥ
    -0.25
    eral
    -0.25
    åĴĮæĶ¯æĮģ
    -0.25
    POSITIVE LOGITS
    nis
    0.27
    æīij
    0.27
    rouch
    0.26
    luet
    0.24
    "↵↵
    0.23
     Summon
    0.23
    lus
    0.23
    (Float
    0.23
     drowned
    0.23
    ización
    0.22
    Activations Density 0.197%

    No Known Activations

    This feature has no known activations.