© 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. 34182
    Prev
    Next
    INDEX
    Explanations

    holistic approach

    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
    Ö¼
    -0.10
    -0.10
    cente
    -0.09
    žd
    -0.09
    à§įত
    -0.09
    ELLOW
    -0.09
    кÑĥл
    -0.09
    ì§ģ
    -0.09
    á»ģn
    -0.09
    andan
    -0.09
    POSITIVE LOGITS
    à¹Ĩ
    0.09
    åĴĮ
    0.08
    verständlich
    0.07
    æĪĸéĥ¨åĪĨ
    0.07
    iment
    0.07
    ÑĶÑĹ
    0.07
    åĮĸ管çIJĨ
    0.07
    ÑĶÑİ
    0.07
    اÙĨÙĬØ©
    0.07
    ificates
    0.07
    Activations Density 0.001%

    No Known Activations