© 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. 15275
    Prev
    Next
    INDEX
    Explanations

    moieties, groups, pin

    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
     ','.
    -0.07
    ç¾Ĭç¾Ĭ
    -0.07
    ãĥĴãĥ¼
    -0.07
    urt
    -0.07
    éro
    -0.07
    æĻ°
    -0.07
    деÑı
    -0.07
    .tp
    -0.07
    .getLogger
    -0.06
    esak
    -0.06
    POSITIVE LOGITS
    è¿Ļæł·çļĦä¸Ģ个
    0.08
    ົ
    0.07
     attachment
    0.07
     attached
    0.07
    å°Ĩä¸Ģ个
    0.07
     dangling
    0.07
     abbreviation
    0.07
    abbrev
    0.07
    èµĦæł¼è¦ģæ±Ĥ
    0.07
    éħĴ
    0.06
    Activations Density 0.008%

    No Known Activations