© 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. 34038
    Prev
    Next
    INDEX
    Explanations

    numbers and categories

    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
    ubi
    -0.07
    å¹¶è¿Ľ
    -0.07
    _console
    -0.07
    jež
    -0.06
    emis
    -0.06
    bjerg
    -0.06
    ãģ¤ãģĦ
    -0.06
    继
    -0.06
    è½¬çľ¼
    -0.06
    anz
    -0.06
    POSITIVE LOGITS
    以åıĬä¸ĢäºĽ
    0.11
    åıĬéĥ¨åĪĨ
    0.10
     maupun
    0.10
    以åıĬåľ¨
    0.09
    è¿Ļ两ç§į
    0.09
    以åıĬ
    0.09
     ataupun
    0.09
    两ç§įæĸ¹å¼ı
    0.09
    åĴĮéĥ¨åĪĨ
    0.08
     oraz
    0.08
    Activations Density 0.518%

    No Known Activations