© 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. 27411
    Prev
    Next
    INDEX
    Explanations

    all but

    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
    ikel
    -0.08
     jun
    -0.07
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    -0.07
    yntax
    -0.06
    ä¸Ĭä¹ĺ
    -0.06
    @email
    -0.06
    rin
    -0.06
    aks
    -0.06
    olec
    -0.06
    ặn
    -0.06
    POSITIVE LOGITS
     except
    0.24
    except
    0.21
    éĻ¤
    0.19
    Except
    0.19
     Except
    0.18
    éĻ¤äºĨ
    0.18
     sauf
    0.16
     kecuali
    0.16
     кÑĢоме
    0.15
    _except
    0.15
    Activations Density 0.180%

    No Known Activations