© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30364
    Prev
    Next
    INDEX
    Explanations

    .

    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
     Apl
    -0.06
    r
    -0.06
    **
    -0.06
    -
    -0.06
    |
    -0.06
     s
    -0.06
    人
    -0.06
    æĦļ
    -0.05
    "
    -0.05
    ob
    -0.05
    POSITIVE LOGITS
    icÃŃ
    0.09
    æĪijè¡Į
    0.09
    vait
    0.08
    ondi
    0.08
    arkin
    0.08
    issé
    0.08
    éĹ®é¢ĺåĪĨæŀIJ
    0.08
    æĸ°æĺŁ
    0.08
    uvé
    0.08
    preh
    0.08
    Activations Density 0.006%

    No Known Activations