© 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. 40239
    Prev
    Next
    INDEX
    Explanations

    php comment blocks

    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
    apolis
    -0.09
    noz
    -0.08
    ebbero
    -0.08
    izable
    -0.08
    æĺ¯åĢ¼å¾Ĺ
    -0.08
    æĺ¯åIJ¦ç¬¦åIJĪ
    -0.08
    ränk
    -0.08
    ogie
    -0.08
    符åIJĪè¦ģæ±Ĥ
    -0.07
    ána
    -0.07
    POSITIVE LOGITS
    æĬĬéĴ±
    0.08
    iest
    0.07
     lass
    0.07
    otra
    0.06
    imb
    0.06
    ç´§ç´§åĽ´ç»ķ
    0.06
    olia
    0.06
    shade
    0.06
    unj
    0.06
    åıĬ以ä¸ĬçļĦ
    0.06
    Activations Density 0.030%

    No Known Activations