© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19304
    Prev
    Next
    INDEX
    Explanations

    registered numbers and letters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĥ³å¾ĹåĪ°
    -0.06
    æĪĸåĪłéĻ¤
    -0.06
    飻
    -0.06
    ä¸įæīĵ
    -0.06
    æľīå¿ĥ
    -0.05
    fond
    -0.05
    å·´å·´
    -0.05
    aldas
    -0.05
     Kl
    -0.05
    cly
    -0.05
    POSITIVE LOGITS
    اضÙĬ
    0.05
    abela
    0.05
     mens
    0.05
     mũ
    0.05
     compliments
    0.05
    rer
    0.05
    ÑĩÑĸ
    0.05
    bezog
    0.05
    ariat
    0.05
     Shia
    0.05
    Activations Density 0.007%

    No Known Activations