© 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. 22226
    Prev
    Next
    INDEX
    Explanations

    Romantic period, composer, style

    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
    å¹³çĶŁ
    -0.07
    riend
    -0.07
     यà¥ĭà¤Ĺ
    -0.07
    åħ¬éģĵ
    -0.07
    æĽ´çĶŁ
    -0.07
    表çļĦ
    -0.07
    åįĥç§ĭ
    -0.06
    bare
    -0.06
    ä¸Ģæµģ
    -0.06
    _courses
    -0.06
    POSITIVE LOGITS
    -era
    0.12
    æĹ¶æľŁ
    0.09
     era
    0.08
    æĹ¶æľŁçļĦ
    0.08
    以éĻį
    0.08
    è¿Ļ个éĺ¶æ®µ
    0.08
    è¿Ļ个æĹ¶ä»£
    0.08
    /post
    0.08
    ä¸İçݰ代
    0.08
    ä¸İæĸ°
    0.08
    Activations Density 0.017%

    No Known Activations