© 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. 42928
    Prev
    Next
    INDEX
    Explanations

    fixed point and uniqueness

    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
    âu
    -0.07
    åĵ¨
    -0.07
    íĻĶëIJľ
    -0.07
    бÑĢе
    -0.07
    ç¥Ńå¥ł
    -0.07
    _SENT
    -0.07
    kaan
    -0.07
    keb
    -0.07
    .sent
    -0.07
    _detector
    -0.07
    POSITIVE LOGITS
     Lips
    0.11
     lips
    0.08
    Ban
    0.08
     Ban
    0.08
    è¿Ń代
    0.08
    æįº
    0.08
    ä¸ĥæĺŁ
    0.08
    æĶ¶æķĽ
    0.07
    åª
    0.07
    éħĿ
    0.07
    Activations Density 0.006%

    No Known Activations