© 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. 8624
    Prev
    Next
    INDEX
    Explanations

    deviations and non-standard behavior

    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
    eho
    -0.08
    rand
    -0.08
    æĹłç§ģçļĦ
    -0.07
    çĻ½é©¬
    -0.07
    大åħ¬
    -0.07
     одина
    -0.07
     thuáºŃn
    -0.07
    oloc
    -0.07
    idth
    -0.07
    vice
    -0.07
    POSITIVE LOGITS
     deviations
    0.11
     deviation
    0.10
    åģı离
    0.09
    è¶ħåĩºäºĨ
    0.08
     dev
    0.08
     depart
    0.08
     violates
    0.08
    ä¿®æĶ¹
    0.08
    æݨ翻
    0.08
     breakdown
    0.08
    Activations Density 0.023%

    No Known Activations