© 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. 38758
    Prev
    Next
    INDEX
    Explanations

    introducing problems

    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
    ssen
    -0.09
    ä¸įåı¯æĢķ
    -0.09
    quist
    -0.08
     DECR
    -0.08
    ÙĤدر
    -0.08
    amani
    -0.08
    ggi
    -0.08
    åIJīæĸ¯
    -0.08
     miser
    -0.08
    olas
    -0.08
    POSITIVE LOGITS
     concept
    0.06
    æļĹ示
    0.06
     implications
    0.06
    pot
    0.06
     implicitly
    0.06
    è¦ģçŁ¥éģĵ
    0.06
     implication
    0.06
    æ½ľåľ¨
    0.06
     computational
    0.05
     Unless
    0.05
    Activations Density 0.004%

    No Known Activations