© 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. 46197
    Prev
    Next
    INDEX
    Explanations

    list of dictionaries or objects

    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
    ia
    -0.07
    åıĬéĥ¨åĪĨ
    -0.06
    utherland
    -0.06
    亦çĦ¶
    -0.06
    [,]
    -0.06
     subTitle
    -0.06
    åıĪæĺ¯
    -0.06
    åįģç«ł
    -0.06
    æ¶Ī
    -0.06
    URN
    -0.06
    POSITIVE LOGITS
    æľīå¥ĸ
    0.08
    umfang
    0.08
    åıĭ
    0.07
    oxel
    0.07
    éĥ½æľīåĵªäºĽ
    0.07
    onstruk
    0.07
    ":[{"
    0.07
     Umfang
    0.07
    å¯¹æľ¬æ¬¡
    0.07
    emade
    0.07
    Activations Density 0.005%

    No Known Activations