© 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. 23921
    Prev
    Next
    INDEX
    Explanations

    blow outs

    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
    ALSE
    -0.09
    rawl
    -0.09
    aceous
    -0.09
    yal
    -0.08
    enary
    -0.08
    ially
    -0.08
    iphy
    -0.08
    ester
    -0.08
    abri
    -0.08
    emento
    -0.08
    POSITIVE LOGITS
    à¸Ķà¹Į
    0.08
    åĺĺ
    0.08
    åĴĮ
    0.07
    ÑģÑı
    0.07
    ong
    0.07
    ↵
    0.07
    baugh
    0.07
    åį³éĢĿ
    0.07
    -out
    0.06
    outs
    0.06
    Activations Density 0.070%

    No Known Activations