© 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. 8771
    Prev
    Next
    INDEX
    Explanations

    separation, deference, touch, sacrifice, release, attacking source

    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
    å·¡
    -0.06
    .Named
    -0.06
    åĢĻ
    -0.06
    åıĬ个人
    -0.06
    åĴĮä¸ŃåĽ½
    -0.06
    ifact
    -0.06
    å§Ķä¼ļ
    -0.06
    该éķĩ
    -0.06
    纲
    -0.06
    formatter
    -0.06
    POSITIVE LOGITS
    æĪĸåĪłéĻ¤
    0.08
    iveness
    0.08
    ting
    0.07
    人ä¸İ人
    0.07
    strup
    0.07
    osi
    0.07
    ç£ģ带
    0.07
    ging
    0.07
    chk
    0.07
    åıijçĶŁåľ¨
    0.07
    Activations Density 0.030%

    No Known Activations