© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59459
    Prev
    Next
    INDEX
    Explanations

    publications and reports

    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
    Negative Logits
    æłĢ
    -0.11
    reff
    -0.09
    æ³IJ
    -0.09
    èµĺ
    -0.09
    blink
    -0.08
    orado
    -0.08
    çģ½
    -0.08
    éģĬ
    -0.08
    天èĬ±
    -0.08
    â¾ı
    -0.08
    POSITIVE LOGITS
     ведÑĮ
    0.10
    åıijçĥ§
    0.09
    sa
    0.09
    ìłij
    0.09
    åĻİ
    0.09
    anges
    0.09
    alyzer
    0.09
    itional
    0.08
    exion
    0.08
    ange
    0.08
    Activations Density 0.007%

    No Known Activations