© 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. 24042
    Prev
    Next
    INDEX
    Explanations

    after prefixes ending in letters

    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
    éd
    -0.08
    aix
    -0.07
    olé
    -0.06
    ลำ
    -0.06
    ced
    -0.06
    åŀĴ
    -0.06
    urig
    -0.06
    าà¸ļ
    -0.06
    angelo
    -0.06
    xis
    -0.06
    POSITIVE LOGITS
    bro
    0.08
    ofstream
    0.07
    çŃīä¼łç»Ł
    0.07
    -vs
    0.07
    ä»ĸä¿©
    0.07
    /W
    0.07
    Vs
    0.07
    åIJĮç±»
    0.07
    à¸Ńุ
    0.07
    ائÙĤ
    0.07
    Activations Density 0.236%

    No Known Activations