© 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. 22386
    Prev
    Next
    INDEX
    Explanations

    feedback and iterative adaptation

    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
    vince
    -0.08
    claimer
    -0.08
    è¯ŃæĸĩèĢģå¸Ī
    -0.08
    为éļ¾
    -0.07
    PackageManager
    -0.07
    ymar
    -0.07
    æĥ³æĸ¹
    -0.07
     Entrev
    -0.07
    æ°ijäºĭè¡Į为èĥ½åĬĽ
    -0.07
    ignum
    -0.07
    POSITIVE LOGITS
     feedback
    0.19
    åıįé¦Ī
    0.19
    feedback
    0.18
    Feedback
    0.17
     Feedback
    0.17
    -feedback
    0.16
    _feedback
    0.14
    è¿Ń代
    0.13
    åıĬæŶåıįé¦Ī
    0.13
     iterative
    0.12
    Activations Density 0.041%

    No Known Activations