© 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. 47508
    Prev
    Next
    INDEX
    Explanations

    nuances, smoking-gun, putative

    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
    arz
    -0.08
    ivas
    -0.08
    ulli
    -0.08
    iskas
    -0.07
    giv
    -0.07
    Ãłng
    -0.07
    Ùħاغ
    -0.07
    гле
    -0.07
    éķ¿éĿĴ
    -0.07
    hum
    -0.07
    POSITIVE LOGITS
    esia
    0.07
    iest
    0.07
    aes
    0.06
    inata
    0.06
    acio
    0.06
    earing
    0.06
    sworth
    0.06
    asuk
    0.06
    ä½ij
    0.06
    ÏĩÏį
    0.06
    Activations Density 0.235%

    No Known Activations