© 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. 150757
    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
     Actors
    -0.28
    azzi
    -0.26
    arnings
    -0.25
    ç´ł
    -0.25
     coll
    -0.24
    åij¼åĶ¤
    -0.24
    ä»ij
    -0.24
     crawl
    -0.23
    éļĨ
    -0.23
    !I
    -0.23
    POSITIVE LOGITS
    秦çļĩ
    0.29
    è°ĥæŁ¥æĺ¾ç¤º
    0.27
    ä¹Łä¸įä¾ĭå¤ĸ
    0.26
    ’e
    0.24
    //===
    0.23
    æĦį
    0.23
    ainer
    0.23
     LinearLayout
    0.23
    çİĩè¾¾åĪ°
    0.23
    èĢĮè¨Ģ
    0.23
    Activations Density 0.905%

    No Known Activations

    This feature has no known activations.