© 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. 22423
    Prev
    Next
    INDEX
    Explanations

    numbers and descriptions

    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
    åѦæŶ
    -0.08
     sekian
    -0.07
    abase
    -0.07
    aman
    -0.07
     kamar
    -0.07
    ensk
    -0.07
    żÄħ
    -0.07
    erland
    -0.07
    abda
    -0.07
    æľīåģ¿
    -0.06
    POSITIVE LOGITS
    iland
    0.08
    åľ¨è¿Ļ段æŶéĹ´
    0.07
    å½¢
    0.07
    ingi
    0.07
    exact
    0.07
    æ©
    0.07
    [random
    0.07
    random
    0.07
     altrett
    0.07
    è¿Ļ个æķ°åŃĹ
    0.06
    Activations Density 0.423%

    No Known Activations