© 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. 7945
    Prev
    Next
    INDEX
    Explanations

    IF conditional

    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
     EITHER
    -0.07
    evo
    -0.07
    med
    -0.07
    身åIJİçļĦ
    -0.07
    éĺħè¯»æľ¬æĸĩ
    -0.07
     déro
    -0.07
    isz
    -0.07
    aston
    -0.06
    çĢı
    -0.06
    Ĥ¤
    -0.06
    POSITIVE LOGITS
    å¤Ł
    0.08
    çļĦè¯Ŀ
    0.08
    è¯Ń
    0.08
    ä¸įå¤Ł
    0.07
    å¤ĸ人
    0.07
     latter
    0.07
    yg
    0.06
    åı£æ°Ķ
    0.06
    oux
    0.06
    ross
    0.06
    Activations Density 0.027%

    No Known Activations