© 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. 23816
    Prev
    Next
    INDEX
    Explanations

    zero, roots, cross, locations

    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
    abbr
    -0.08
    icul
    -0.07
     teil
    -0.07
    nowrap
    -0.07
    Cycle
    -0.07
     ctypes
    -0.07
    ncmp
    -0.07
    xCD
    -0.07
     chu
    -0.06
     (('
    -0.06
    POSITIVE LOGITS
    å¤§æľ¬
    0.08
    天éŨ
    0.08
    лÑĮÑĤа
    0.07
     locations
    0.07
    idders
    0.07
     location
    0.07
    æ´ŀ
    0.07
    éļIJèĹıåľ¨
    0.07
    idget
    0.07
    æĹłè¸ª
    0.07
    Activations Density 0.001%

    No Known Activations