© 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. 41519
    Prev
    Next
    INDEX
    Explanations

    No. / Pat. No

    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
    [][
    -0.07
    ets
    -0.07
    ä¸ŃéĢļ
    -0.07
    коÑĢи
    -0.07
    ESH
    -0.07
    iology
    -0.07
    彿
    -0.07
    ä¹ĭ称çļĦ
    -0.07
    çİĭçļĦ
    -0.07
    ocol
    -0.07
    POSITIVE LOGITS
    åīį款
    0.07
    auft
    0.07
     consequently
    0.06
    byn
    0.06
    积åĪĨ
    0.06
    æĦıè§ģ建议
    0.06
    æıIJä¾Ľç»Ļ
    0.06
    uin
    0.06
    è®°
    0.06
    ÑģÑĤеÑĢ
    0.06
    Activations Density 0.001%

    No Known Activations