© 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. 47542
    Prev
    Next
    INDEX
    Explanations

    BSD or MIT license

    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
    çĥĺ
    -0.09
    ISC
    -0.09
    جÙĦس
    -0.08
    ãģĦãģŁãģł
    -0.08
    anko
    -0.08
    ontology
    -0.08
    æݥ管
    -0.08
    пÑĢав
    -0.08
    aph
    -0.08
    arry
    -0.08
    POSITIVE LOGITS
    樽
    0.10
    tere
    0.08
    æݧèĤ¡
    0.08
    è°Į
    0.08
    主è¦ģæľī
    0.08
    ãģ¾
    0.08
    å°¹
    0.08
    çĦ¶æĺ¯
    0.08
    çģ«èĬ±
    0.08
     Epstein
    0.08
    Activations Density 0.012%

    No Known Activations