© 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. 19040
    Prev
    Next
    INDEX
    Explanations

    maximal value or limit

    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
    tribu
    -0.08
    áĥĶáĥłáĥĹ
    -0.07
    ulasi
    -0.07
    yard
    -0.07
    amento
    -0.07
    ording
    -0.07
    MASTER
    -0.07
    ئÛĴ
    -0.07
    er
    -0.06
    erb
    -0.06
    POSITIVE LOGITS
    IMUM
    0.12
    bows
    0.08
    imized
    0.08
    zew
    0.08
    nesia
    0.07
    0.07
    ÂŃi
    0.07
    itudes
    0.07
    秫
    0.07
    hely
    0.07
    Activations Density 0.004%

    No Known Activations