© 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. 12238
    Prev
    Next
    INDEX
    Explanations

    kind or type of

    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
    agic
    -0.10
    esthetic
    -0.10
    æľīåĪ©
    -0.10
     меÑĢ
    -0.10
    éķ°
    -0.10
    opsy
    -0.10
    ä¸Ģ个æĺ¯
    -0.10
    æ±°
    -0.09
    è¿ĺæľīä¸Ģ个
    -0.09
    箪
    -0.09
    POSITIVE LOGITS
    类似çļĦ
    0.08
    Ấ
    0.08
    çĶļ
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.07
    ฯ
    0.07
    æ³Ľ
    0.07
     Pf
    0.07
    åĿļ
    0.07
    rs
    0.07
     kind
    0.07
    Activations Density 0.177%

    No Known Activations