© 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. 40924
    Prev
    Next
    INDEX
    Explanations

    prefix un- / non- / ac- / bil- / hyp-

    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
    θÎŃν
    -0.08
    ANGO
    -0.08
    formas
    -0.08
    adeiras
    -0.08
    itats
    -0.08
    ências
    -0.07
    ANDO
    -0.07
    ichts
    -0.07
    ATORS
    -0.07
    ÏĮν
    -0.07
    POSITIVE LOGITS
    ermann
    0.07
    <<<
    0.07
    èĢĮåĸ»
    0.07
    kow
    0.07
    /non
    0.07
    ault
    0.07
    esn
    0.06
    overe
    0.06
    äºİ
    0.06
    aj
    0.06
    Activations Density 0.023%

    No Known Activations