© 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. 43357
    Prev
    Next
    INDEX
    Explanations

    sentiment and performance evaluation

    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
     futile
    -0.08
    ä¸Ģæİ¢
    -0.08
    太éĩį
    -0.07
    ÑĪнÑı
    -0.07
     ngây
    -0.07
    áro
    -0.07
    åħ·æľīçļĦ
    -0.07
    æ¦Ħ
    -0.07
    åįļ大
    -0.07
     mistakenly
    -0.07
    POSITIVE LOGITS
    èī¯å¥½
    0.12
    没æľīåĩºçİ°
    0.11
    èī¯å¥½çļĦ
    0.11
    没æľīéĹ®é¢ĺ
    0.10
     satisfactory
    0.10
    åIJĦæĸ¹éĿ¢
    0.10
     good
    0.10
     неплоÑħо
    0.10
    å¾Ĺå¾Ī好
    0.09
    éĥ½ä¸įéĶĻ
    0.09
    Activations Density 0.617%

    No Known Activations