© 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. 21929
    Prev
    Next
    INDEX
    Explanations

    thanks and help

    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
    rans
    -0.05
     carn
    -0.05
    责令
    -0.05
    ä¸įå¿ħè¦ģçļĦ
    -0.05
    rend
    -0.05
    cole
    -0.05
     dul
    -0.05
    aving
    -0.05
    uhl
    -0.05
    èĩªè§īåľ°
    -0.05
    POSITIVE LOGITS
    -fly
    0.06
    æĭįåĪ°
    0.06
    æł¼å¼ıçļĦ
    0.06
    å¤ĩ注
    0.06
    æ¬ł
    0.06
     Pon
    0.05
    (mi
    0.05
    çĩİ
    0.05
    å¾Īå¤ļæľĭåıĭ
    0.05
    æł¼å¼ı
    0.05
    Activations Density 0.002%

    No Known Activations