© 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. 50060
    Prev
    Next
    INDEX
    Explanations

    examination and review

    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
    为åħ¶
    -0.07
    egend
    -0.07
     addict
    -0.07
    inya
    -0.07
    两åĢį
    -0.07
    _Info
    -0.07
    eh
    -0.07
    ILLE
    -0.07
    äºĪ
    -0.06
    åĨ°å²Ľ
    -0.06
    POSITIVE LOGITS
    -Ta
    0.07
    è¦ģæ±ĤåIJĦ
    0.07
    æ¯ı个
    0.07
    .every
    0.07
    ä¸ŃæĪIJéķ¿
    0.07
    æ±Ĥ羣
    0.07
    åIJĪæł¼çļĦ
    0.06
    符åIJĪè¦ģæ±Ĥ
    0.06
     eval
    0.06
     íıīê°Ģ를
    0.06
    Activations Density 0.001%

    No Known Activations