© 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. 49618
    Prev
    Next
    INDEX
    Explanations

    cubic extension, coding, crypt, Iglesias, Solomon

    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
    åĬ³åĬ¨åħ³ç³»
    -0.07
    jum
    -0.07
    HTMLElement
    -0.07
    ilat
    -0.07
    æ´¥
    -0.06
    å¤ļæĥ³
    -0.06
    åİ»ä½ķ
    -0.06
    Stat
    -0.06
    åįĥ人
    -0.06
    ä¹ı
    -0.06
    POSITIVE LOGITS
    inom
    0.08
     Bits
    0.08
    ouro
    0.08
    sept
    0.07
    hia
    0.07
    è¿Ľåİ»
    0.07
    åĵĶ
    0.07
    /bit
    0.07
    çĸ¯
    0.07
    ç«ĭæĸ°
    0.07
    Activations Density 0.005%

    No Known Activations