© 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. 38819
    Prev
    Next
    INDEX
    Explanations

    intent.putextra ID

    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
    åĩŃ
    -0.07
    Pager
    -0.07
    iliation
    -0.07
    oints
    -0.07
    repair
    -0.07
    rank
    -0.07
    antically
    -0.07
    Rank
    -0.06
    oint
    -0.06
    rames
    -0.06
    POSITIVE LOGITS
    lemen
    0.08
    бан
    0.07
    åĩĢé¢Ŀ
    0.07
    ãģ¾ãģªãģĦ
    0.07
    loed
    0.06
    תר
    0.06
    mine
    0.06
    uhi
    0.06
    ç»´äºļ
    0.06
    oger
    0.06
    Activations Density 0.003%

    No Known Activations