© 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. 60507
    Prev
    Next
    INDEX
    Explanations

    plenty of, lots of, tons of

    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
    æIJŃéħįä¸Ĭ
    -0.08
    дÑĢÑĥ
    -0.08
    è¢ħè¢ħ
    -0.08
    ä»»ä½ķäºĭæĥħ
    -0.08
    åħ¨éĥ¨è´£ä»»
    -0.08
    æĶ¶èĹıæľ¬ç«Ļ
    -0.08
    éĥ¨åĪĨåĨħ容
    -0.08
    æľīæīĢæĢĿ
    -0.07
    etag
    -0.07
     geheel
    -0.07
    POSITIVE LOGITS
     sayıda
    0.11
    å¤ļçļĦ
    0.10
    ness
    0.10
     sekali
    0.09
     (>
    0.09
    -needed
    0.09
    кÑĢаÑĤно
    0.08
    å¹´æĿ¥
    0.08
    ened
    0.08
    次çļĦ
    0.08
    Activations Density 0.221%

    No Known Activations