© 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. 28699
    Prev
    Next
    INDEX
    Explanations

    code assignments and structures

    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
     shifting
    -0.07
     shifted
    -0.07
    ç¼ĵ
    -0.07
    éĩijåĪļ
    -0.07
    shift
    -0.07
     shifts
    -0.06
     Neves
    -0.06
    .shift
    -0.06
     conting
    -0.06
    èij«èĬ¦
    -0.06
    POSITIVE LOGITS
    elis
    0.07
    åĿı
    0.07
    æĥľ
    0.07
    å®īå¨ľ
    0.07
    OGO
    0.07
    ovat
    0.07
    gis
    0.07
    IMS
    0.07
    å¤ĸçĶ¨
    0.07
    ovnÃŃ
    0.07
    Activations Density 0.040%

    No Known Activations