© 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. 26279
    Prev
    Next
    INDEX
    Explanations

    whether we

    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
    quel
    -0.07
    ½
    -0.07
    orium
    -0.07
    angep
    -0.07
    resta
    -0.07
    åĬłå¿«å»ºè®¾
    -0.07
    åıªåĽł
    -0.07
    combe
    -0.07
    oria
    -0.07
    inning
    -0.07
    POSITIVE LOGITS
    suma
    0.07
    код
    0.07
    代ä¹ĭ
    0.07
    oused
    0.07
    usto
    0.07
    (dc
    0.06
    .Microsoft
    0.06
    ssize
    0.06
    ìļ´
    0.06
     âĵĴ
    0.06
    Activations Density 0.004%

    No Known Activations