© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30158
    Prev
    Next
    INDEX
    Explanations

    lo mismo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ly
    -0.11
    æĸ°çļĦä¸Ģ
    -0.09
    urally
    -0.09
     모ìĬµ
    -0.09
    ments
    -0.09
    ily
    -0.09
    è¿Ļæīį
    -0.09
    mente
    -0.09
    è¿Ļç§įæĸ¹æ³ķ
    -0.08
    身åIJİ
    -0.08
    POSITIVE LOGITS
    PTION
    0.10
     mismo
    0.09
    aring
    0.09
    oter
    0.09
    ÄŁ
    0.09
    ayar
    0.09
    轸
    0.08
    ä»ŀ
    0.08
    ç¾İçļĦ
    0.08
    ANDLE
    0.08
    Activations Density 0.036%

    No Known Activations