© 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. 65394
    Prev
    Next
    INDEX
    Explanations

    function $\ln$ or $\sin$

    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
    iril
    -0.07
    èĤīçľ¼
    -0.07
    arci
    -0.06
    angk
    -0.06
    é¸Ń
    -0.06
     abst
    -0.06
    /cgi
    -0.06
    说åĪ°è¿ĻéĩĮ
    -0.06
    _unused
    -0.06
    arp
    -0.06
    POSITIVE LOGITS
     delayed
    0.08
    å»¶è¿Ł
    0.08
    chon
    0.08
    ussa
    0.08
    enni
    0.08
    æĸ°åŀĭçļĦ
    0.07
    æİ¨è¿Ł
    0.07
     Delay
    0.07
    -delay
    0.07
    imia
    0.07
    Activations Density 0.008%

    No Known Activations