© 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. 16763
    Prev
    Next
    INDEX
    Explanations

    actions and processes

    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
    ouser
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    azzino
    -0.06
    æĮĸæİĺåħ¬åı¸
    -0.06
    ertif
    -0.06
    renc
    -0.06
     miliar
    -0.06
    LATED
    -0.06
    غب
    -0.06
     establecidos
    -0.06
    POSITIVE LOGITS
    ett
    0.05
    轩
    0.05
    il
    0.05
    urun
    0.05
    ç¾½
    0.05
    èĮĥ
    0.05
    ghan
    0.05
     pros
    0.05
    ä¹ĭè·¯
    0.05
    ätz
    0.05
    Activations Density 0.079%

    No Known Activations