© 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. 12280
    Prev
    Next
    INDEX
    Explanations

    custom objects or types

    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
    quil
    -0.07
    verse
    -0.07
     reversed
    -0.06
    osa
    -0.06
    ister
    -0.06
    §
    -0.06
    临
    -0.06
    æķ°ä¸įæ¸ħ
    -0.06
    YM
    -0.06
     Lynch
    -0.06
    POSITIVE LOGITS
    лаÑģ
    0.08
    lopedia
    0.08
    ç§
    0.08
    лик
    0.08
    ror
    0.08
    porto
    0.08
    çĶ¨ä»¥
    0.07
    incinn
    0.07
    ideon
    0.07
    ,:,:
    0.07
    Activations Density 0.002%

    No Known Activations