© 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. 21145
    Prev
    Next
    INDEX
    Explanations

    remember that

    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
    ely
    -0.06
    utta
    -0.06
    оÑĤно
    -0.06
    éĻ¥
    -0.05
    unia
    -0.05
    åķĨåѦéĻ¢
    -0.05
    minen
    -0.05
     these
    -0.05
    elly
    -0.05
     favor
    -0.05
    POSITIVE LOGITS
    èĩªçĦ¶æĺ¯
    0.06
    Bợi
    0.06
    太éĥİ
    0.06
    bote
    0.06
    ä¸Ģ座
    0.06
    acruz
    0.06
    ваÑıÑģÑĮ
    0.06
    ãģĦãĤĮãģ°
    0.05
    çķĶ
    0.05
    æĢ§å¥½
    0.05
    Activations Density 0.001%

    No Known Activations