© 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. 29592
    Prev
    Next
    INDEX
    Explanations

    reviewing or checking data

    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
    ghan
    -0.08
    éijij
    -0.08
    ignon
    -0.08
    aksi
    -0.08
    uhan
    -0.08
    jaz
    -0.07
    äºĨä¸Ģ件
    -0.07
    äºĨä¸Ģé¢Ĺ
    -0.07
    Enumer
    -0.07
     âĢº
    -0.07
    POSITIVE LOGITS
    æľī没æľī
    0.15
    æĺ¯åIJ¦æľī
    0.14
    æĺ¯åIJ¦åŃĺåľ¨
    0.12
    æľīæĹł
    0.11
    æľīæ²Ĵæľī
    0.11
    ä½łæľī没æľī
    0.10
     carefully
    0.10
     whether
    0.10
    æĺ¯ä¸įæĺ¯
    0.09
    ä¸Ń寻æī¾
    0.09
    Activations Density 0.169%

    No Known Activations