© 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. 21682
    Prev
    Next
    INDEX
    Explanations

    price

    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
    ä¸įæĢ¥
    -0.06
    o
    -0.06
     parameters
    -0.05
     oby
    -0.05
    APS
    -0.05
    Bl
    -0.05
    LOW
    -0.05
    ç¼ĸ
    -0.05
    ahul
    -0.05
    çļĦæľĢé«ĺ
    -0.05
    POSITIVE LOGITS
    imak
    0.06
    ä¸įæķ¢
    0.06
    æģ¯
    0.06
    æģ¯çļĦ
    0.05
    æľī误
    0.05
     beneficial
    0.05
    deel
    0.05
     Herbst
    0.05
     enjo
    0.05
     medo
    0.05
    Activations Density 0.051%

    No Known Activations