© 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. 7984
    Prev
    Next
    INDEX
    Explanations

    something particular

    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
    uct
    -0.07
    rant
    -0.07
     impuls
    -0.07
    estro
    -0.07
    aven
    -0.07
    åĬł
    -0.07
    éĻ¤éĿŀ
    -0.07
    åIJ«
    -0.07
    onto
    -0.06
    ç»ıçIJĨ
    -0.06
    POSITIVE LOGITS
    beck
    0.08
    æĻ´
    0.07
     Schild
    0.07
    æĪijåĴĮæĪijçļĦ
    0.07
    /vendors
    0.07
    åŁºå°¼
    0.07
    éĹ®é¢ĺ解åĨ³
    0.07
    屬
    0.07
    大大å°ı
    0.07
    ruÄį
    0.07
    Activations Density 0.001%

    No Known Activations