© 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. 56849
    Prev
    Next
    INDEX
    Explanations

    large memory usage/storage

    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
     rút
    -0.08
     пÑĢомо
    -0.08
    pekt
    -0.07
    elos
    -0.07
    ledon
    -0.07
    à¸Īัà¸ĩหวะ
    -0.07
    toupper
    -0.07
    åıijçĶµæľºç»Ħ
    -0.07
    æĺ¯ä¸Ģå¹´
    -0.07
     horn
    -0.06
    POSITIVE LOGITS
     storage
    0.13
     storing
    0.12
    åŃĺåĤ¨
    0.12
    åŃĺåĤ¨ç©ºéĹ´
    0.11
     Storage
    0.11
    storage
    0.10
    åŃĺæĶ¾
    0.10
     ÑħÑĢанениÑı
    0.10
    æķ°æį®åŃĺåĤ¨
    0.10
    .storage
    0.10
    Activations Density 0.039%

    No Known Activations