© 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. 27836
    Prev
    Next
    INDEX
    Explanations

    only followed by a verb

    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
    anos
    -0.10
    eger
    -0.09
    ấn
    -0.09
    ัà¸ĩหว
    -0.09
    colas
    -0.09
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.08
     demais
    -0.08
    edr
    -0.08
    Clr
    -0.08
    CanBe
    -0.08
    POSITIVE LOGITS
    å¤ł
    0.10
    ä¹Łåıªèĥ½
    0.07
    éģĵéģĵ
    0.07
    éĿłèĩªå·±
    0.07
    çľ¼çĿģçĿģ
    0.07
    lah
    0.07
    berra
    0.06
    èĢĮä¸įèĥ½
    0.06
    n
    0.06
    rc
    0.06
    Activations Density 0.006%

    No Known Activations