© 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. 16671
    Prev
    Next
    INDEX
    Explanations

    a part of

    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
    Ñģполни
    -0.11
    pray
    -0.11
    ibera
    -0.10
    elib
    -0.10
    å°ĶèĴĻ
    -0.10
    ervis
    -0.10
     dikat
    -0.10
    ÑģполÑĮзÑĥй
    -0.10
    Kelu
    -0.10
    çľ¯çľ¯
    -0.10
    POSITIVE LOGITS
    ,
    0.09
    -
    0.08
    ↵
    0.08
    0.08
    '
    0.08
    *
    0.08
    1
    0.08
    Âł
    0.08
    D
    0.07
    ï¼Į
    0.07
    Activations Density 0.107%

    No Known Activations