© 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. 18341
    Prev
    Next
    INDEX
    Explanations

    namespace declaration

    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
    urface
    -0.06
    çİĭçīĮ
    -0.06
    ÙģاÙģ
    -0.06
    appareil
    -0.06
    valho
    -0.06
    ieber
    -0.06
    ç§įç±»çļĦ
    -0.06
    atson
    -0.06
    æĪij身边
    -0.06
    éĿ¢çĽ¸
    -0.06
    POSITIVE LOGITS
    less
    0.06
    å°Ħ
    0.06
    ed
    0.05
     concurrent
    0.05
    èµ
    0.05
    åħĭèݱ
    0.05
    Lets
    0.05
    etag
    0.05
    æĿĢ
    0.05
    reamble
    0.05
    Activations Density 0.025%

    No Known Activations