© 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. 25493
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

    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
    tourn
    -0.08
    æĶĺ
    -0.08
    odel
    -0.07
    ovah
    -0.07
    jee
    -0.07
    вле
    -0.07
    derive
    -0.07
    Rotation
    -0.07
    AndWait
    -0.07
    åľĨ满çļĦ
    -0.07
    POSITIVE LOGITS
    ater
    0.07
    å¤§ä½ľ
    0.07
    rp
    0.07
     Ofic
    0.06
    su
    0.06
    lund
    0.06
    ONTAL
    0.06
    å°±ç®ĹäºĨ
    0.06
    inds
    0.06
    è¿ĺæľīæľºä¼ļ
    0.06
    Activations Density 0.071%

    No Known Activations