© 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. 22029
    Prev
    Next
    INDEX
    Explanations

    differences/connections between topics

    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
    å·¢
    -0.07
    ãħ
    -0.06
    /animations
    -0.06
    ulte
    -0.06
    æ¥
    -0.06
    åıĸæ¶Īåħ¶
    -0.06
    تابعة
    -0.06
     наÑĢ
    -0.06
    spir
    -0.06
    ucker
    -0.06
    POSITIVE LOGITS
    lev
    0.05
    è´±
    0.05
    opan
    0.05
    isan
    0.05
    assing
    0.05
    çıį妮
    0.05
    åįĥä¼ı
    0.05
    ader
    0.05
    colari
    0.05
    openh
    0.05
    Activations Density 0.043%

    No Known Activations