© 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. 42005
    Prev
    Next
    INDEX
    Explanations

    optional increases

    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
    å¤įåĪ¶æĪĸ
    -0.10
     appunto
    -0.09
     insomma
    -0.08
    ä½łåij¢
    -0.08
    iggers
    -0.08
    æĬķèµĦæĪĸ
    -0.08
     esp
    -0.08
    /Form
    -0.08
    VT
    -0.08
    ä¸ĭåIJĮ
    -0.07
    POSITIVE LOGITS
     tzv
    0.08
     sogenannte
    0.07
    åı«åģļ
    0.07
    çī¹æ®ĬçļĦ
    0.07
     seperate
    0.07
    uchi
    0.06
    åĪ«æľī
    0.06
     tzw
    0.06
     reportedly
    0.06
    åİŁæĿ¥
    0.06
    Activations Density 0.804%

    No Known Activations