© 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. 50356
    Prev
    Next
    INDEX
    Explanations

    is X? or happens when X?

    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
     Pera
    -0.07
    arder
    -0.07
     SKIP
    -0.06
    andr
    -0.06
    åıĭ们
    -0.06
    кÑĢе
    -0.06
    çĤ¹å¯¹
    -0.06
    веÑĨ
    -0.06
    æŀľ
    -0.06
    墩
    -0.06
    POSITIVE LOGITS
     запÑĢо
    0.08
    olong
    0.08
    culus
    0.07
    ç¬Ļ
    0.07
    olg
    0.07
    æ¯Ķè¾ĥæľī
    0.07
    бли
    0.07
    PGA
    0.07
     -->
    0.07
     Reyn
    0.07
    Activations Density 0.003%

    No Known Activations