© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42833
    Prev
    Next
    INDEX
    Explanations

    industry leader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ỽ
    -0.07
    å¥Īä½ķ
    -0.07
    istic
    -0.07
    plicht
    -0.06
    æŶåħī
    -0.06
     campaigners
    -0.06
    diff
    -0.06
     ÙĪبر
    -0.06
    å½¢å¼ıçļĦ
    -0.06
    еÑģпÑĥбли
    -0.06
    POSITIVE LOGITS
    ustry
    0.10
    -wide
    0.10
    éļĪ
    0.10
    è¿Ļ个è¡Įä¸ļ
    0.09
    åħ¬è®¤çļĦ
    0.09
     vá»±c
    0.09
     industry
    0.09
    verband
    0.09
    wide
    0.09
    åħ¬è®¤
    0.08
    Activations Density 0.336%

    No Known Activations