© 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. 30190
    Prev
    Next
    INDEX
    Explanations

    "video" or "audio" reports

    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
     personalised
    -0.08
    ocking
    -0.07
     slugg
    -0.07
    éĿĴæ¢ħ
    -0.07
    æľīèī²
    -0.07
     ``(
    -0.07
     neighbouring
    -0.07
     authorised
    -0.07
    thu
    -0.06
    azol
    -0.06
    POSITIVE LOGITS
    åĪ°åŃ¦æł¡
    0.06
     Fle
    0.06
    åıªå·®
    0.06
    onie
    0.06
    bjerg
    0.06
    çŃīå¾ħ
    0.06
    hea
    0.06
    DIC
    0.06
    å°Ĩæĺ¯
    0.06
    ÑĤÑĮе
    0.06
    Activations Density 0.092%

    No Known Activations