© 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. 58760
    Prev
    Next
    INDEX
    Explanations

    prestwich

    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
    -0.07
    æĪİ
    -0.07
    åİŁ
    -0.07
    ç®Ĺ
    -0.07
     (
    -0.06
    âĺ
    -0.06
    ев
    -0.06
    ï¼Ī
    -0.06
    èĢ¿
    -0.06
    åĢ¾
    -0.06
    POSITIVE LOGITS
     INFORMA
    0.09
    ohlen
    0.09
    åįģä¸ĥç«ł
    0.09
    è´£ç¼ĸ
    0.09
    cius
    0.09
    ütt
    0.09
    upal
    0.09
    ä¹ŁæĽ´
    0.08
    ä¹ĭéŨ
    0.08
    wiet
    0.08
    Activations Density 0.008%

    No Known Activations