© 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. 13515
    Prev
    Next
    INDEX
    Explanations

    some X are

    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
     presumably
    -0.10
    å¤ļåįĬ
    -0.10
     mostly
    -0.10
    สà¹Īวà¸Ļà¹ĥหà¸įà¹Ī
    -0.09
     usually
    -0.09
     largely
    -0.09
    大å¤ļ
    -0.09
    ä¸ĢèĪ¬ä¸įä¼ļ
    -0.09
    大æ¦Ĥçİĩ
    -0.09
     generally
    -0.08
    POSITIVE LOGITS
     addirittura
    0.15
    çĶļèĩ³æĺ¯
    0.13
     sogar
    0.12
     dokonce
    0.12
     downright
    0.12
    çĶļèĩ³åľ¨
    0.11
    çĶļèĩ³ä¼ļ
    0.11
    íķĺ기ëıĦ
    0.11
    çĶļèĩ³
    0.11
     persino
    0.10
    Activations Density 0.180%

    No Known Activations