© 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. 787
    Prev
    Next
    INDEX
    Explanations

    control of vehicle and wheels

    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
    èĥĮçĿĢ
    -0.09
    æIJŀ
    -0.09
    å·´å·´
    -0.09
    æIJŀå¾Ĺ
    -0.09
     Hind
    -0.09
    åĬĽæ°Ķ
    -0.08
    å°Ĭ
    -0.08
    çĦ°
    -0.08
    çĹ°
    -0.08
    adies
    -0.08
    POSITIVE LOGITS
    ords
    0.10
    ãĥķãĤ¡
    0.09
    ä¸į失
    0.09
    ours
    0.09
    bine
    0.09
    åĻ
    0.09
    ulla
    0.09
     shr
    0.09
    ìĮį
    0.08
    æľ¬çĶ°
    0.08
    Activations Density 0.012%

    No Known Activations