© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61631
    Prev
    Next
    INDEX
    Explanations

    evaluating aspects

    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
    antai
    -0.09
    大æľīåı¯ä¸º
    -0.08
    嬢
    -0.07
    ajari
    -0.07
     keting
    -0.07
    大ä¸Ī夫
    -0.07
    ebro
    -0.07
    aldi
    -0.07
    locator
    -0.07
    lest
    -0.07
    POSITIVE LOGITS
     ìĸ¼ë§ĪëĤĺ
    0.12
     ability
    0.12
    ãģ©ãĤĮãģłãģij
    0.11
    æľīæĹł
    0.11
    æĺ¯åIJ¦èĥ½å¤Ł
    0.10
    æľī没æľī
    0.10
     Ability
    0.10
    æĺ¯åIJ¦
    0.10
    èĥ½åIJ¦
    0.10
    Ability
    0.10
    Activations Density 0.079%

    No Known Activations