© 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. 29919
    Prev
    Next
    INDEX
    Explanations

    lodash documentation comments

    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
    riqu
    -0.07
    åħīæ´ģ
    -0.07
    ä»Ķ
    -0.06
     Laure
    -0.06
    .testing
    -0.06
    æŃ£ç¡®çļĦ
    -0.06
    please
    -0.06
    sap
    -0.06
    upp
    -0.06
    åħ®
    -0.06
    POSITIVE LOGITS
    çĻ¾åIJį
    0.07
    åĩºèµ°
    0.07
    æľīæīĢæĢĿ
    0.07
    红ç³ĸ
    0.07
    ezu
    0.07
    /logout
    0.07
    esar
    0.07
    åºĶå¾ģ
    0.07
    æݧèĤ¡éĽĨåĽ¢æľīéĻIJåħ¬åı¸
    0.07
    éºĵ
    0.07
    Activations Density 0.079%

    No Known Activations