© 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. 33237
    Prev
    Next
    INDEX
    Explanations

    parameters and rooms, second

    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
    éļı便
    -0.07
    pper
    -0.06
    amel
    -0.06
    çĹ´
    -0.06
     Lever
    -0.06
    chie
    -0.06
     Pep
    -0.06
    ä¸Ģ个æĺŁæľŁ
    -0.06
    æ³³
    -0.06
    apel
    -0.06
    POSITIVE LOGITS
    éĻ¤äºĨ
    0.11
    第äºĮéĥ¨åĪĨ
    0.09
    éĻ¤
    0.09
    第äºĮéĺ¶æ®µ
    0.09
    第ä¸īæŃ¥
    0.09
     beyond
    0.09
    第ä¸īç§į
    0.09
    second
    0.09
    第äºĮç§į
    0.08
    _second
    0.08
    Activations Density 0.263%

    No Known Activations