© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57114
    Prev
    Next
    INDEX
    Explanations

    private key, health, method, network, repo, APIs, cars

    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
    spel
    -0.09
    ingly
    -0.09
    rapy
    -0.09
    träger
    -0.09
     xuôi
    -0.09
    abez
    -0.09
    اتÙĩا
    -0.08
    ujur
    -0.08
    å¹³åİŁ
    -0.08
    asper
    -0.08
    POSITIVE LOGITS
    OperationException
    0.07
    /private
    0.07
    ities
    0.07
    -sector
    0.07
    ization
    0.07
    ĸ
    0.07
    ÃŃsimo
    0.07
    ÃŃssimo
    0.07
    /public
    0.06
    -looking
    0.06
    Activations Density 0.041%

    No Known Activations