© 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. 51214
    Prev
    Next
    INDEX
    Explanations

    `@` or `$` followed by name

    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
    ály
    -0.08
     Grie
    -0.08
    _MAKE
    -0.08
    UIL
    -0.07
    è±
    -0.07
     chac
    -0.07
    说æĿ¥
    -0.07
    ugh
    -0.07
    ahu
    -0.07
     assunto
    -0.07
    POSITIVE LOGITS
    âĢ
    0.07
    ä»İä¸ŃåĽ½
    0.06
    ender
    0.06
     Mon
    0.06
     mê
    0.06
     Main
    0.06
    æ¢ħ
    0.06
    éĿ©
    0.06
    {{{
    0.06
    åijĢ
    0.06
    Activations Density 0.001%

    No Known Activations