© 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. 4727
    Prev
    Next
    INDEX
    Explanations

    gears, cranks, wheels, cams

    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
    产èĥ½
    -0.09
    ç¾½
    -0.08
    è¯Ŀ说
    -0.08
    åľ¨æĦı
    -0.08
    èµı
    -0.08
    icorn
    -0.08
    /ion
    -0.08
     jspb
    -0.08
     Bes
    -0.08
    åĩĨ
    -0.08
    POSITIVE LOGITS
     dys
    0.09
    ulg
    0.09
    èĿİ
    0.09
    éű
    0.09
    Comm
    0.09
    _comm
    0.09
    Circular
    0.09
    .comm
    0.08
    ä¸ĢåIJij
    0.08
    éļ°
    0.08
    Activations Density 0.056%

    No Known Activations