© 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. 64190
    Prev
    Next
    INDEX
    Explanations

    skill level or expertise

    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
    æĹłåIJį
    -0.08
    èį¡èį¡
    -0.08
    utable
    -0.07
    äºĪ
    -0.07
    äºİè¡Į
    -0.07
     putin
    -0.07
     ìŬ
    -0.06
    posable
    -0.06
    çİīæłij
    -0.06
     Rout
    -0.06
    POSITIVE LOGITS
    dessus
    0.07
    ä½ĨæľĢç»Ī
    0.07
     acima
    0.07
    åĽ½å®¶æĶ¿çŃĸ
    0.07
    æĪijå·²
    0.07
    æıIJçĤ¼
    0.07
    ÑĥмаÑĤÑĮ
    0.07
     dessus
    0.07
     justified
    0.06
     REFERENCES
    0.06
    Activations Density 0.002%

    No Known Activations