© 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. 34029
    Prev
    Next
    INDEX
    Explanations

    quoting "someone" saying

    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
    Õ¸ÖĤÕ¶
    -0.07
    Latch
    -0.07
     Shades
    -0.07
    ×ķ×ķ
    -0.07
    麹
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    ео
    -0.07
    &p
    -0.07
    rang
    -0.06
    "<?
    -0.06
    POSITIVE LOGITS
     “âĢ¦
    0.08
    仪
    0.08
    çĶ¨æ³ķ
    0.08
    ä¾ĭåı¥
    0.07
    åĦĢ
    0.07
    illot
    0.07
    ÙĬÙĦØ©
    0.07
    acen
    0.07
    iente
    0.07
     referring
    0.07
    Activations Density 0.062%

    No Known Activations