© 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. 42903
    Prev
    Next
    INDEX
    Explanations

    roman numerals

    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
    este
    -0.07
     kia
    -0.06
    اص
    -0.06
    ago
    -0.06
    S
    -0.06
    ãģĽ
    -0.06
    zit
    -0.06
    ³
    -0.06
    çļĦåİŁ
    -0.06
    è¿Ļ家åħ¬åı¸
    -0.06
    POSITIVE LOGITS
    udar
    0.08
    alti
    0.08
    äºļçī¹
    0.08
    ffit
    0.08
    aison
    0.08
    öd
    0.08
    áºŃn
    0.08
    aight
    0.08
    æ´Ľä¼Ĭ
    0.08
    taa
    0.08
    Activations Density 0.059%

    No Known Activations