© 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. 55673
    Prev
    Next
    INDEX
    Explanations

    current method or developing knowledge

    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
    ideo
    -0.08
    ®
    -0.08
    qli
    -0.08
    trinsic
    -0.07
    rites
    -0.07
    partis
    -0.07
    ÑħнÑĥÑĤÑĮ
    -0.07
    enciales
    -0.07
    å¥Ĺ
    -0.07
    èĬ·
    -0.07
    POSITIVE LOGITS
    å°±æīĵ
    0.07
    адÑĮ
    0.06
     mention
    0.06
    æ°´åĻ¨
    0.06
    åĿŀ
    0.06
    emap
    0.06
     War
    0.06
    othi
    0.06
    åģı
    0.06
    uje
    0.06
    Activations Density 1.055%

    No Known Activations