© 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. 20142
    Prev
    Next
    INDEX
    Explanations

    code structures and options

    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
    ä¼Ĺ
    -0.07
    ivable
    -0.07
    çī¹å°Ķ
    -0.07
    ÑĩиÑĤ
    -0.07
    æ¬ł
    -0.07
    åºĶ交
    -0.07
    ussin
    -0.07
    anie
    -0.07
    å¥ĩçļĦ
    -0.07
    asil
    -0.07
    POSITIVE LOGITS
    antino
    0.08
    ambre
    0.07
    è¿Ľä¸ĢæŃ¥åıijå±ķ
    0.07
    æĸ½æķĻ
    0.07
    渴
    0.07
    abal
    0.07
    广度
    0.07
    ewolf
    0.06
     dying
    0.06
    æĿIJ
    0.06
    Activations Density 0.003%

    No Known Activations