© 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. 58489
    Prev
    Next
    INDEX
    Explanations

    currency codes (USD, EUR)

    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
    foot
    -0.07
    è·¯ä¸İ
    -0.07
    æ±
    -0.07
    ylic
    -0.06
    ibli
    -0.06
    ä¸į计
    -0.06
    èĤĭ
    -0.06
    åľ¨åı°æ¹¾
    -0.06
     seg
    -0.06
    URN
    -0.06
    POSITIVE LOGITS
    æ¯Ķèĩªå·±
    0.08
    ÑĩаÑģа
    0.08
    ipt
    0.08
    rior
    0.07
    ارس
    0.07
    'email
    0.07
    rie
    0.07
    Designer
    0.07
    æ¯Ķä»ĸ
    0.07
     fria
    0.07
    Activations Density 0.006%

    No Known Activations