© 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. 33191
    Prev
    Next
    INDEX
    Explanations

    complexities, issues, and aspects

    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
    piece
    -0.08
    smith
    -0.07
    éĢ¢
    -0.07
     piece
    -0.07
    ICY
    -0.06
    agner
    -0.06
    zett
    -0.06
    berge
    -0.06
    æľīä¸ĢèĤ¡
    -0.06
    lecht
    -0.06
    POSITIVE LOGITS
    ities
    0.11
    ÏĪειÏĤ
    0.09
    ures
    0.09
    aciones
    0.09
    coes
    0.09
    URES
    0.09
    legate
    0.09
    诸å¦Ĥ
    0.09
    ноÑģÑĤÑıÑħ
    0.09
    ements
    0.08
    Activations Density 0.657%

    No Known Activations