© 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. 12833
    Prev
    Next
    INDEX
    Explanations

    parts, portions, core, main, rest

    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
    eller
    -0.07
    version
    -0.07
    ä¸Ģæĸ¹çļĦ
    -0.06
    好çī©
    -0.06
    mia
    -0.06
    gem
    -0.06
    _both
    -0.06
     version
    -0.06
     pauses
    -0.06
     Greenwood
    -0.06
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.09
    éĤ£åĩłä¸ª
    0.08
    éch
    0.08
    èĩªçĶ±
    0.08
    _SA
    0.07
    ÐIJÐĹ
    0.07
    红çģ«
    0.07
     Arbitrary
    0.07
    ĶĦ
    0.07
    éļıå¿ĥæīĢ欲
    0.07
    Activations Density 0.018%

    No Known Activations