© 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. 25884
    Prev
    Next
    INDEX
    Explanations

    websites ending in .com / .info

    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
    IGE
    -0.08
    严äºİ
    -0.08
    igem
    -0.07
    Ñģном
    -0.07
     Sih
    -0.07
    &utm
    -0.07
    kamp
    -0.07
    ennen
    -0.07
    (Unit
    -0.07
    为åįķä½į
    -0.07
    POSITIVE LOGITS
    aku
    0.07
    azu
    0.06
    zor
    0.06
    leo
    0.06
    èij±èij±
    0.06
    Ñĩай
    0.06
    ohen
    0.06
    ochond
    0.06
    acles
    0.06
    uo
    0.06
    Activations Density 0.140%

    No Known Activations