© 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. 24321
    Prev
    Next
    INDEX
    Explanations

    plasma mirror

    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
    çĪª
    -0.07
    æŁĵ
    -0.06
    æĦıä¹īéĩį大
    -0.06
    å¾ĹæĽ´åĬł
    -0.06
    éĻĪ
    -0.06
    éĿ¢å±Ĥ
    -0.06
    ://{
    -0.06
    Opens
    -0.06
     hybrid
    -0.06
    åIJIJ
    -0.05
    POSITIVE LOGITS
     ë§
    0.08
    ä½łæĢİä¹Ī
    0.08
    SSI
    0.08
    arez
    0.08
    reten
    0.08
    elig
    0.08
    lda
    0.08
    人ä¼ļ
    0.08
    å§ĭç¥ĸ
    0.08
    æīĭåĬ¨
    0.07
    Activations Density 0.137%

    No Known Activations