© 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. 24425
    Prev
    Next
    INDEX
    Explanations

    load sharing

    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
    ï¸İ
    -0.10
    LogLevel
    -0.08
    acor
    -0.08
    ÙĤاÙĦ
    -0.07
    å¦ĻçļĦ
    -0.07
    chor
    -0.07
    ergestellt
    -0.07
    angelo
    -0.07
    è·¯ä¸ľ
    -0.07
     ÐĿали
    -0.07
    POSITIVE LOGITS
    ings
    0.13
    INGS
    0.09
    iton
    0.08
    -bearing
    0.08
    ÙĤØ©
    0.08
    azan
    0.08
    ening
    0.08
    IRECT
    0.07
    indsay
    0.07
    ä¼į
    0.07
    Activations Density 0.042%

    No Known Activations