© 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. 16483
    Prev
    Next
    INDEX
    Explanations

    selection car list

    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
    avent
    -0.07
    å°±åĪ«
    -0.07
    é©¾é©¶æľºåĬ¨è½¦
    -0.07
     Amend
    -0.07
    ongodb
    -0.07
    å®ļçĦ¶
    -0.07
    иÑĤоÑĢ
    -0.07
    omia
    -0.07
    ohn
    -0.07
    /gif
    -0.07
    POSITIVE LOGITS
    erty
    0.08
     BÃŃ
    0.08
    代
    0.07
    ourt
    0.07
    etta
    0.07
    uchen
    0.07
    VIC
    0.07
    essori
    0.06
    oup
    0.06
    æģ¯
    0.06
    Activations Density 0.027%

    No Known Activations