© 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. 40058
    Prev
    Next
    INDEX
    Explanations

    introduction headings

    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
    hing
    -0.07
    å§Ķ
    -0.07
    .Done
    -0.06
    иÑİ
    -0.06
    omic
    -0.06
    è¿Ļ个åĵģçīĮ
    -0.06
     ren
    -0.06
     اÙĦØŃÙĬÙĪÙĬØ©
    -0.06
    åĪĿæģĭ
    -0.06
    ionic
    -0.06
    POSITIVE LOGITS
    ãģĿãĤĤãģĿãĤĤ
    0.09
    kaç
    0.08
    个人è§ĤçĤ¹
    0.07
    ç§ij大åѦ
    0.07
    ç®ĢæŀIJ
    0.07
    ãģªãģľ
    0.07
    eve
    0.07
    STS
    0.07
    দà§įধ
    0.07
    ================================
    0.07
    Activations Density 0.004%

    No Known Activations