© 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. 2769
    Prev
    Next
    INDEX
    Explanations

    mix, permits, create, MySQL, consumed, grow

    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
    éģ©
    -0.07
     instead
    -0.07
    Äįer
    -0.07
    rax
    -0.06
    éĽĨåĽ¢èĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.06
    åħ´åĽ½
    -0.06
    çıį
    -0.06
    xit
    -0.06
     Fed
    -0.06
    acı
    -0.06
    POSITIVE LOGITS
    fels
    0.09
    olec
    0.08
    ifique
    0.08
     ëĭ´ê¸´
    0.07
     Allein
    0.07
    àµįà´¯
    0.07
    麽
    0.07
    被ä»ĸ
    0.07
     пÑĢоведен
    0.07
    çī
    0.07
    Activations Density 1.019%

    No Known Activations