© 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. 20665
    Prev
    Next
    INDEX
    Explanations

    study findings or results

    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
     fame
    -0.08
    åħ¨ç§°
    -0.07
    ÙĦاء
    -0.07
    ains
    -0.07
     undergo
    -0.06
     dites
    -0.06
    ocup
    -0.06
     fiche
    -0.06
    åIJįåŃĹåı«
    -0.06
    åĪĨ为
    -0.06
    POSITIVE LOGITS
    ç»ĵæŀľæĺ¾ç¤º
    0.08
    æľ¬çłĶ究
    0.08
    éĢļè¿ĩæľ¬æ¬¡
    0.08
    ç»ĵæŀľè¡¨æĺİ
    0.08
    results
    0.08
    ä»ĬåĽŀãģ®
    0.08
    åĩºçİ°äºĨ
    0.08
    æľĿå¤ķ
    0.08
     albeit
    0.08
    asco
    0.08
    Activations Density 0.282%

    No Known Activations