© 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. 6477
    Prev
    Next
    INDEX
    Explanations

    may be or might be

    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
    çĦī
    -0.10
    egis
    -0.09
    aze
    -0.09
     Fare
    -0.09
    æ´²
    -0.09
    кÑĢов
    -0.08
    饲
    -0.08
    åIJ¯ç¤º
    -0.08
    uchen
    -0.08
    ÕŃ
    -0.08
    POSITIVE LOGITS
     Clarkson
    0.10
    ãģªãģıãģ¦ãĤĤ
    0.10
    á»ĩt
    0.09
     deb
    0.09
    oot
    0.09
     Cro
    0.09
    解åĨ³äºĨ
    0.09
    æĺ¯ä¸Ģéĥ¨
    0.09
    éļıæīĭ
    0.09
    Cro
    0.09
    Activations Density 0.036%

    No Known Activations