© 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. 17796
    Prev
    Next
    INDEX
    Explanations

    coordinates preceded by `(`

    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
    )
    -0.08
    rock
    -0.07
    ch
    -0.07
    ing
    -0.06
     *
    -0.06
    oc
    -0.06
    ).
    -0.06
    }
    -0.06
    al
    -0.06
    éģİ
    -0.06
    POSITIVE LOGITS
    ähler
    0.09
    icitÃł
    0.09
    DataContract
    0.08
    Agenzia
    0.08
    ÃŃculas
    0.08
    uforia
    0.08
    acruz
    0.08
    achel
    0.08
    adelphia
    0.08
    aches
    0.08
    Activations Density 0.013%

    No Known Activations