© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63046
    Prev
    Next
    INDEX
    Explanations

    verbs followed by descriptions

    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
    åĬłæĭ¿å¤§
    -0.10
    æĸ°åĬłåĿ¡
    -0.10
    ç®Ģ称
    -0.08
    åĴĮ第
    -0.08
    ç²¾ç¥ŀä¸Ĭ
    -0.06
    以ä¸ĭç®Ģ称
    -0.06
    ari
    -0.06
    pp
    -0.06
    <|box_end|>
    -0.06
    arie
    -0.06
    POSITIVE LOGITS
    ambang
    0.09
    omos
    0.08
    ä¸Ģéĥİ
    0.08
    addon
    0.08
    çļĦéĤ£å¤©
    0.08
    æĹ©çŁ¥éģĵ
    0.08
    åĴĮèĶ¬èıľ
    0.08
    à®Łà¯Ī
    0.07
    ontra
    0.07
    aeda
    0.07
    Activations Density 0.667%

    No Known Activations