© 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. 7773
    Prev
    Next
    INDEX
    Explanations

    simplified implementation

    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
    رÙĨ
    -0.08
    äºĨæĮĩ
    -0.08
    .si
    -0.08
    _fu
    -0.07
    oren
    -0.07
    ردة
    -0.07
    æ´»åĬ¨ç»ĵæĿŁåIJİ
    -0.07
    åĪ¶ä½ľå·¥èīº
    -0.07
    _atts
    -0.07
    çŁ¥éģĵæĪij
    -0.07
    POSITIVE LOGITS
    åĩ¡
    0.07
    toy
    0.06
     patter
    0.06
    对æѤ
    0.06
     Python
    0.06
    åĪ°æѤ
    0.06
    éĿĴæ¢ħ
    0.06
     NONE
    0.06
    æľīåij³
    0.06
    luck
    0.06
    Activations Density 0.003%

    No Known Activations