© 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. 23390
    Prev
    Next
    INDEX
    Explanations

    battery life

    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
    身价
    -0.08
    æ±Ĥ羣
    -0.07
    æĭįæīĭ
    -0.07
    ALLE
    -0.07
    æµ®èºģ
    -0.07
    ediator
    -0.07
    achinery
    -0.07
    .compress
    -0.07
    ì¸ł
    -0.07
    ssä
    -0.07
    POSITIVE LOGITS
     replen
    0.13
    èĢĹå°½
    0.13
     depleted
    0.13
    åĤ¨å¤ĩ
    0.12
     refill
    0.12
    çºĮ
    0.11
     запаÑģ
    0.11
    ç»ŃèĪª
    0.11
     depletion
    0.11
    çĶ¨å®Į
    0.10
    Activations Density 0.082%

    No Known Activations