© 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. 64714
    Prev
    Next
    INDEX
    Explanations

    special characters and numbers

    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
    emb
    -0.07
    ond
    -0.07
    è¿ĻäºĽæķ°æį®
    -0.06
    aat
    -0.06
    åĸľæ°Ķ
    -0.06
    éģĵæĿ¥
    -0.06
    æĵ¦
    -0.06
    reed
    -0.06
    мÑı
    -0.06
    åIJijéĺ³
    -0.06
    POSITIVE LOGITS
    ynes
    0.08
    ä¹ĭä¸ī
    0.08
    èĢģäºĮ
    0.08
    ä¸ī人
    0.08
    (rotation
    0.08
     thirds
    0.08
     cyclic
    0.08
    ascus
    0.08
    olate
    0.08
    çĤ¯
    0.08
    Activations Density 0.002%

    No Known Activations