© 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. 28528
    Prev
    Next
    INDEX
    Explanations

    introducing more specific details

    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
    -collapse
    -0.08
    è§Ħ
    -0.07
    ιÏİ
    -0.07
    agy
    -0.07
    lim
    -0.07
     Erb
    -0.07
    implified
    -0.07
    лили
    -0.07
    aney
    -0.07
    IMIT
    -0.07
    POSITIVE LOGITS
    ä¸įå½±åĵį
    0.10
    ä¸įä¼ļå½±åĵį
    0.09
     irrelevant
    0.08
     arbitrary
    0.08
     harmless
    0.07
    æĹĭ
    0.07
    ä¸įåľ¨ä¹İ
    0.07
     unrelated
    0.07
     altering
    0.07
    æĹłåħ³
    0.07
    Activations Density 0.004%

    No Known Activations