© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61883
    Prev
    Next
    INDEX
    Explanations

    worry about whether

    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
    ruik
    -0.09
    iture
    -0.09
    apg
    -0.09
    å°±ç®ĹäºĨ
    -0.09
    AMED
    -0.09
    elok
    -0.09
    иÑģÑĤеÑĢ
    -0.09
    ারণ
    -0.08
    ác
    -0.08
    mers
    -0.08
    POSITIVE LOGITS
     whether
    0.10
    æĺ¯åIJ¦
    0.08
    æĺ¯åIJ¦ä¸İ
    0.07
    æĺ¯åIJ¦åľ¨
    0.07
    :
    0.06
    æĺ¯åIJ¦æľī
    0.06
    æĺ¯åIJ¦ä¸º
    0.06
    æĺ¯åIJ¦æŃ£ç¡®
    0.06
    æĺ¯åIJ¦æĺ¯
    0.06
     subtle
    0.06
    Activations Density 0.005%

    No Known Activations