© 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. 41235
    Prev
    Next
    INDEX
    Explanations

    mean curvature

    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
    æ´Ĺå®Į
    -0.08
    weer
    -0.08
    çĨĦ
    -0.08
    iena
    -0.07
    apol
    -0.07
    richt
    -0.07
    åĿıäºĨ
    -0.07
    è·¤
    -0.07
    课é¢ĺç»Ħ
    -0.07
    æĹ©é¤IJåIJİ
    -0.07
    POSITIVE LOGITS
    åĴĮåIJĦ
    0.08
    annen
    0.07
    èĨ¨èĥĢ
    0.07
    /global
    0.07
     summed
    0.07
    æĶ¶ç¼©
    0.07
    åĽ
    0.07
    åıĬåIJĦ
    0.07
    æĬķéĻį
    0.06
     efect
    0.06
    Activations Density 0.002%

    No Known Activations