© 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. 922
    Prev
    Next
    INDEX
    Explanations

    options or multiple choice answers

    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
    LEV
    -0.07
    lev
    -0.07
    utam
    -0.07
    å®ļä½į为
    -0.07
    çļĦ人è¿ĺ
    -0.06
    缴æİ¥æĪĸ
    -0.06
    urz
    -0.06
    ÃŃb
    -0.06
    èĭ¦è¾£
    -0.06
    ÐĶФ
    -0.06
    POSITIVE LOGITS
    tas
    0.09
    wf
    0.08
    请éĢīæĭ©
    0.08
    ведено
    0.07
    thon
    0.07
    ilder
    0.07
    &e
    0.07
    0.06
    ITAS
    0.06
    itas
    0.06
    Activations Density 0.007%

    No Known Activations