© 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. 31033
    Prev
    Next
    INDEX
    Explanations

    essential component or part

    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
    æľĢèijĹåIJįçļĦ
    -0.08
    eben
    -0.08
     quickest
    -0.07
    å¾Īæľī趣
    -0.07
    ä¸ºçĽ®çļĦ
    -0.07
    BUFFER
    -0.07
    祺
    -0.07
     simplest
    -0.07
     gerne
    -0.07
     easiest
    -0.07
    POSITIVE LOGITS
     indispensable
    0.11
    ä¸įåı¯æĪĸ缺
    0.11
     indispensables
    0.10
     essential
    0.10
    essential
    0.10
     vital
    0.09
     critical
    0.09
    çĶŁæŃ»
    0.09
    çĶļèĩ³åľ¨
    0.09
    éĽªä¸Ń
    0.08
    Activations Density 0.079%

    No Known Activations