© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22667
    Prev
    Next
    INDEX
    Explanations

    an introduction to something

    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
    undes
    -0.07
    æīĢ欲
    -0.07
    nus
    -0.07
    illy
    -0.07
    代ä¹ĭ
    -0.06
    unek
    -0.06
    /animations
    -0.06
    ëĭ¹ìĿĺ
    -0.06
    ety
    -0.06
    æķĻåѦç»ıéªĮ
    -0.06
    POSITIVE LOGITS
     olyan
    0.15
     whose
    0.15
    whose
    0.13
    à¸ģรà¸ĵีà¸Ĺีà¹Ī
    0.12
     wherein
    0.11
    à¹Ģà¸ģมà¸Ĺีà¹Ī
    0.11
     cuyos
    0.11
     à¤IJसा
    0.11
     whereby
    0.11
    jenigen
    0.11
    Activations Density 0.916%

    No Known Activations