© 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. 18251
    Prev
    Next
    INDEX
    Explanations

    not exhaustive or complete

    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
    resent
    -0.06
    æĭīå¼Ģ
    -0.06
    hlas
    -0.06
    é²ľæĺİçļĦ
    -0.06
    pread
    -0.06
     merce
    -0.06
    ê°ĸ
    -0.06
     Tenemos
    -0.05
    osso
    -0.05
    çļĭ
    -0.05
    POSITIVE LOGITS
    ampe
    0.06
    å¿ħè¦ģçļĦ
    0.06
    ÑĢÑĥз
    0.06
     Bull
    0.05
    èį£
    0.05
    azzi
    0.05
    abble
    0.05
    ãĤ¹ãĥĨãĥł
    0.05
    imit
    0.05
    åľ¨å¤ĸ
    0.05
    Activations Density 0.003%

    No Known Activations