© 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. 22205
    Prev
    Next
    INDEX
    Explanations

    any character or symbol

    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
    æ³¾
    -0.07
    è¶ĭ
    -0.07
    pth
    -0.07
    æĪijæĦ¿
    -0.07
     manh
    -0.06
    èĢĮéĿŀ
    -0.06
    uentes
    -0.06
    LAM
    -0.06
    _tools
    -0.06
    ke
    -0.06
    POSITIVE LOGITS
     whatsoever
    0.09
     whatever
    0.09
    JNI
    0.08
    nyi
    0.07
    éĥ½ä¸įçĶ¨
    0.07
    whatever
    0.07
    åıįæŃ£
    0.07
     essentially
    0.07
     irrelevant
    0.07
    ×IJ×Ļ×Ŀ
    0.07
    Activations Density 0.028%

    No Known Activations