© 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. 33921
    Prev
    Next
    INDEX
    Explanations

    case study report

    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
    åŃ©åŃIJ们çļĦ
    -0.08
     neutral
    -0.08
     Neutral
    -0.07
    neutral
    -0.07
    çļĦèĩªçĦ¶
    -0.07
    ä¸ŃæĢ§
    -0.07
    Neutral
    -0.07
    åĵªéĩĮæľī
    -0.07
     neutrality
    -0.06
    xDE
    -0.06
    POSITIVE LOGITS
     single
    0.22
    åįķ个
    0.22
    /single
    0.21
    single
    0.20
     SINGLE
    0.20
    åįķä¸Ģ
    0.20
     Single
    0.19
    Single
    0.19
    (single
    0.19
    _single
    0.18
    Activations Density 0.406%

    No Known Activations