© 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. 34705
    Prev
    Next
    INDEX
    Explanations

    radio button, template, value, suggest

    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
    çī¹éĤĢ
    -0.07
    æĪĸå¤ļæĪĸå°ij
    -0.07
    ä¸ĬéŨ
    -0.06
    åĻĤ
    -0.06
    relude
    -0.06
    åıĪæĿ¥äºĨ
    -0.06
     Ñĥгодно
    -0.06
    æĹ©æĬ¥
    -0.06
    çĥŃæIJľ
    -0.06
     Terr
    -0.06
    POSITIVE LOGITS
    éĢīä¸Ń
    0.11
     among
    0.11
    ä¼ļéĢīæĭ©
    0.11
    åľ¨ä¼Ĺå¤ļ
    0.11
    åºĶéĢīæĭ©
    0.10
    éĢī
    0.10
    éĢīæĭ©åĴĮ
    0.10
    éĢīæĭ©
    0.10
     selected
    0.10
    among
    0.10
    Activations Density 0.021%

    No Known Activations