© 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. 27142
    Prev
    Next
    INDEX
    Explanations

    contesting, indulging, chronicling, obtaining, eliciting

    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
    æĺ¯è¦ģ
    -0.06
    ä¸Ģ个æĸ°çļĦ
    -0.06
     przyj
    -0.06
    ÙĪرÙĩا
    -0.06
    inari
    -0.06
    WRAPPER
    -0.06
    çĹ
    -0.06
    åĬªåĬĽå¥ĭæĸĹ
    -0.06
    å·¥ä½ľå§Ķåijĺä¼ļ
    -0.06
    ulaire
    -0.06
    POSITIVE LOGITS
    &o
    0.08
    æľīä¸į
    0.08
    çĻ¾åĪĨä¹ĭçĻ¾
    0.08
    Ñģнов
    0.07
    åıijçĶŁéĩį大
    0.07
    ož
    0.07
    _chance
    0.06
     hợ
    0.06
     Lem
    0.06
    éľ²æ°´
    0.06
    Activations Density 0.327%

    No Known Activations