© 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. 47322
    Prev
    Next
    INDEX
    Explanations

    offering details or features

    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
    åľ¨çĽ®
    -0.08
    :error
    -0.08
    /il
    -0.08
     [/
    -0.08
    åħį费订éĺħ
    -0.07
    çĶ¨å®ĥ
    -0.07
    éħĴå±ĭ
    -0.07
    æīįåı¯ä»¥
    -0.07
    å®ĥåı¯ä»¥
    -0.07
     odw
    -0.07
    POSITIVE LOGITS
    è¿Ļ让æĪij
    0.07
    astre
    0.07
    _language
    0.06
    imu
    0.06
    mie
    0.06
    æ³ī
    0.06
    æ³½æ°ij
    0.06
    ä¸ļåĬ¡åıijå±ķ
    0.06
    _basic
    0.06
    éķ¿èĢģ
    0.06
    Activations Density 2.644%

    No Known Activations