© 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. 39790
    Prev
    Next
    INDEX
    Explanations

    FileCheck

    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
    è¾ĩ
    -0.11
    èĤ¯
    -0.09
    æĶ¾è¿ĩ
    -0.09
    åıĶåıĶ
    -0.09
     limp
    -0.09
    urch
    -0.09
     Tok
    -0.09
     kak
    -0.08
    æŦ
    -0.08
    åıĻäºĭ
    -0.08
    POSITIVE LOGITS
    Æ°u
    0.09
    ç§
    0.09
    ears
    0.09
    éĽĮ
    0.08
    æĺĶ
    0.08
     reusable
    0.08
    便åı¯
    0.08
    ÑĤай
    0.08
    åį³åı¯
    0.08
    agle
    0.08
    Activations Density 0.002%

    No Known Activations