© 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. 59119
    Prev
    Next
    INDEX
    Explanations

    aniel railway abstract

    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
    ors
    -0.06
    åĨķ
    -0.06
    ze
    -0.06
    oup
    -0.06
     fold
    -0.06
    apu
    -0.06
    ise
    -0.06
     cont
    -0.06
    vac
    -0.06
    raj
    -0.06
    POSITIVE LOGITS
    ilians
    0.08
    è¡Įä¹ĭ
    0.08
     rued
    0.08
    ä¹ĭçģ«
    0.08
    ä¸įèĢģ
    0.08
    éĥ½åIJĪ
    0.08
     ÙĦÙĪÙĨ
    0.08
    hell
    0.07
    _errno
    0.07
    åħ³çģ¯
    0.07
    Activations Density 0.026%

    No Known Activations