© 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. 16389
    Prev
    Next
    INDEX
    Explanations

    0 to 1 range

    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
    awai
    -0.08
    éļ¾æ±Ĥ
    -0.07
    è·ĭ
    -0.07
    linger
    -0.07
    ajari
    -0.07
    fixtures
    -0.07
    åīįåIJİ
    -0.07
    envir
    -0.07
    åħĭæĸ¯
    -0.07
     Pac
    -0.06
    POSITIVE LOGITS
    jala
    0.07
    egger
    0.07
     progressive
    0.07
    __.__
    0.07
    ish
    0.06
    -tip
    0.06
    åĩłå¹´çļĦ
    0.06
     tip
    0.06
    nish
    0.06
    以éĺ²
    0.06
    Activations Density 0.006%

    No Known Activations