© 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. 16784
    Prev
    Next
    INDEX
    Explanations

    historical events and figures

    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
    arest
    -0.07
    ittest
    -0.06
    árd
    -0.06
    è¿ĺ没æľī
    -0.06
    åIJijéĺ³
    -0.06
     Müdür
    -0.06
    iesen
    -0.06
    .Cl
    -0.06
    oup
    -0.06
    ialect
    -0.06
    POSITIVE LOGITS
    ä»İæĿ¥
    0.06
    A
    0.05
    L
    0.05
    E
    0.05
    aka
    0.05
     etc
    0.05
    I
    0.05
    0
    0.05
     spar
    0.05
    ~
    0.05
    Activations Density 0.061%

    No Known Activations