© 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. 22603
    Prev
    Next
    INDEX
    Explanations

    variables k and u

    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
    èĿ¶
    -0.08
    æł¼æł¼
    -0.07
    allis
    -0.06
    æģ©
    -0.06
    çļĦæĢĿæĥ³
    -0.06
    Hell
    -0.06
    MF
    -0.06
    _stat
    -0.06
    zf
    -0.06
    ter
    -0.06
    POSITIVE LOGITS
    _RCC
    0.07
    çĻ¾åıĺ
    0.06
    æĶ¾çŁ¢
    0.06
    诣
    0.06
    æŶåı¯
    0.06
    æĬĦ
    0.06
     darken
    0.06
    è¿Ļå°±è¦ģæ±Ĥ
    0.06
     Quarterly
    0.06
     mine
    0.06
    Activations Density 0.016%

    No Known Activations