© 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. 12211
    Prev
    Next
    INDEX
    Explanations

    one-shot

    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
    .getLine
    -0.08
    avigator
    -0.08
    -confirm
    -0.08
    å»ī
    -0.08
    pollo
    -0.08
    zte
    -0.08
    çļĦç¡®
    -0.08
    åij½çļĦ
    -0.07
    Injected
    -0.07
    idata
    -0.07
    POSITIVE LOGITS
    effective
    0.07
     effective
    0.06
    éĶģ骨
    0.06
    Effective
    0.06
     Effective
    0.06
    ÑıÑĤи
    0.06
    orra
    0.06
     pril
    0.06
    progressbar
    0.06
    å¿¿
    0.06
    Activations Density 0.141%

    No Known Activations