© 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. 42038
    Prev
    Next
    INDEX
    Explanations

    South Dakota State Correctional

    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
    fsp
    -0.10
    ifer
    -0.09
    ayah
    -0.08
    оÑģо
    -0.08
    Gol
    -0.08
    ufer
    -0.08
    kah
    -0.08
    ignes
    -0.08
    è®©æĽ´å¤ļ人
    -0.08
    lacer
    -0.08
    POSITIVE LOGITS
    ym
    0.07
    en
    0.07
     sin
    0.06
    Âł
    0.06
    ala
    0.06
    unge
    0.06
    ver
    0.06
    ype
    0.06
    åĬł
    0.06
     par
    0.06
    Activations Density 0.049%

    No Known Activations