© 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. 22441
    Prev
    Next
    INDEX
    Explanations

    discussion lists

    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
    éĺ
    -0.07
    upo
    -0.06
    enville
    -0.06
     mân
    -0.06
     conseg
    -0.06
    表çİ°
    -0.05
    нÑĨе
    -0.05
    rador
    -0.05
    pont
    -0.05
     acond
    -0.05
    POSITIVE LOGITS
    inkan
    0.06
    eras
    0.05
    SHIFT
    0.05
    å·²è¶ħè¿ĩ
    0.05
     Ansprüche
    0.05
    大åŀĭ
    0.05
    Ñĥв
    0.05
    缮åīįå·²ç»ı
    0.05
    å¹´åįİ
    0.05
     past
    0.05
    Activations Density 0.004%

    No Known Activations