© 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. 38376
    Prev
    Next
    INDEX
    Explanations

    spanish "¿" questions

    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
     sostanzi
    -0.07
    æľīçĤ¹
    -0.06
    hest
    -0.06
    ë´IJ
    -0.06
    ël
    -0.06
    ิà¹Ĭà¸ģ
    -0.06
    æĹłåıĮ
    -0.06
    åĴ¨è¯¢çĥŃ线
    -0.06
    没æľīåľ¨
    -0.06
    åĩłä¹İæĺ¯
    -0.06
    POSITIVE LOGITS
    utate
    0.07
    åĻ©
    0.07
    åĽ½å®ī
    0.07
    ETHER
    0.07
    embl
    0.07
    ÙħاÛĮ
    0.07
     derr
    0.07
    _PROF
    0.07
    %B
    0.07
     Inflate
    0.07
    Activations Density 0.050%

    No Known Activations