© 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. 150242
    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
    解éĻ¤
    -0.31
    åľ°ä½į
    -0.31
     noexcept
    -0.28
    Ñħодим
    -0.28
    uez
    -0.27
    ç½®
    -0.27
    igu
    -0.27
    çļĦåľ°ä½į
    -0.27
    æĮĩ
    -0.27
    æĸ¹å¼ıè¿Ľè¡Į
    -0.26
    POSITIVE LOGITS
    è°±
    0.27
     Scenes
    0.26
     Useful
    0.26
    _assignment
    0.25
    ä¸ľè·¯
    0.25
    ffield
    0.25
    -License
    0.25
    æ±¹
    0.24
     Kul
    0.24
     unclear
    0.24
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.