© 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. 50567
    Prev
    Next
    INDEX
    Explanations

    necessity and conditions

    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
    owski
    -0.08
    ocat
    -0.08
    occa
    -0.08
    æł¸åıij
    -0.07
    éĻĪåħĪçĶŁ
    -0.07
    åĤ»åĤ»
    -0.07
     ['$
    -0.07
    umpah
    -0.07
    ocate
    -0.07
    ä¹ĭéķ¿
    -0.07
    POSITIVE LOGITS
     affinché
    0.09
    以ä¸ĭæĿ¡ä»¶
    0.08
     lest
    0.08
    éĻ¤äºĨæľī
    0.07
    æľīä¸ĢæĿ¡
    0.07
    ife
    0.07
     absolument
    0.07
     additionally
    0.07
     supaya
    0.07
     either
    0.07
    Activations Density 0.006%

    No Known Activations