© 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. 65190
    Prev
    Next
    INDEX
    Explanations

    additional

    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
    ollower
    -0.07
    ulo
    -0.07
    idd
    -0.06
    orso
    -0.06
     Allowed
    -0.06
    æ°ijäºĭè¡Į为
    -0.06
    ebb
    -0.06
    orama
    -0.06
    alto
    -0.06
    æĮº
    -0.06
    POSITIVE LOGITS
    以å¤ĸãģ®
    0.11
    以å¤ĸãģ«ãĤĤ
    0.11
     additional
    0.10
     other
    0.10
    åľ¨åħ¶ä»ĸ
    0.10
    çļĦåħ¶ä»ĸ
    0.09
    -other
    0.09
    以å¤ĸçļĦ
    0.09
    _additional
    0.09
    additional
    0.09
    Activations Density 1.011%

    No Known Activations