© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7050
    Prev
    Next
    INDEX
    Explanations

    causal, physical, symmetry, MVC, codes

    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
    Negative Logits
    atform
    -0.09
    बà¥į
    -0.08
    itant
    -0.08
    itants
    -0.08
    Äĥr
    -0.08
    è¿·
    -0.08
    ä¸ĢæĶ¹
    -0.08
    ummy
    -0.08
    天ä¸Ģ
    -0.08
    UMMY
    -0.08
    POSITIVE LOGITS
     requirements
    0.08
     requirement
    0.08
    è¦ģæ±ĤçļĦ
    0.08
     Proper
    0.07
     consistency
    0.07
    è¿Ļå°±è¦ģæ±Ĥ
    0.07
    çļĦåŁºæľ¬è¦ģæ±Ĥ
    0.07
     Requirements
    0.07
     properly
    0.07
     Requirement
    0.07
    Activations Density 0.009%

    No Known Activations