© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21002
    Prev
    Next
    INDEX
    Explanations

    trains teaching staff

    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
    ungg
    -0.07
    æ·±åĪ»åľ°
    -0.06
    ç¸
    -0.06
    волÑİ
    -0.06
    大åħ¬
    -0.06
    пеÑĩаÑĤ
    -0.06
     defaultMessage
    -0.06
    inyin
    -0.06
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.06
    dech
    -0.06
    POSITIVE LOGITS
    udo
    0.05
     Anything
    0.05
     anything
    0.05
    ãĥ¡
    0.05
     Payne
    0.05
    Everything
    0.05
     everything
    0.05
    æŃ¥
    0.05
    icing
    0.05
    æľºæ¢°
    0.05
    Activations Density 0.001%

    No Known Activations