© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22546
    Prev
    Next
    INDEX
    Explanations

    same color, shoes, form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    manifest
    -0.05
    #!
    -0.05
     manifest
    -0.05
    alog
    -0.05
     Manifest
    -0.05
    nam
    -0.05
     manifestation
    -0.05
    ä¸įä¹±
    -0.05
     Cage
    -0.05
    variably
    -0.05
    POSITIVE LOGITS
    isses
    0.07
     functionalities
    0.06
    èĭ«
    0.06
     Villar
    0.06
    usst
    0.06
    å¼ı设计
    0.06
     specifications
    0.06
    essen
    0.06
    othe
    0.05
    使çĶ¨å¹´éĻIJ
    0.05
    Activations Density 0.009%

    No Known Activations