© 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. 60487
    Prev
    Next
    INDEX
    Explanations

    differences between things

    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
    anner
    -0.08
    æľīçļĦåIJĮåѦ
    -0.08
    çĦ¶
    -0.07
    ial
    -0.07
    éģĵçIJĨ
    -0.06
    çĦ¶çļĦ
    -0.06
    èij©
    -0.06
    å¾Īå¤ļåIJĮåѦ
    -0.06
    åıĪå¦Ĥä½ķ
    -0.06
     wasn
    -0.06
    POSITIVE LOGITS
     whereas
    0.11
    æĽ´æ³¨éĩį
    0.09
    侧éĩįäºİ
    0.09
    éĩįåľ¨
    0.08
    使çĶ¨çļĦæĺ¯
    0.08
    åĢ¾åIJijäºİ
    0.08
     hingegen
    0.08
     dagegen
    0.08
    çĿĢçľ¼äºİ
    0.08
    çĶ¨çļĦæĺ¯
    0.08
    Activations Density 0.037%

    No Known Activations