© 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. 60782
    Prev
    Next
    INDEX
    Explanations

    want to / wish to / seeking

    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
    iset
    -0.09
    ONT
    -0.09
    縮
    -0.08
    æ²īéĩį
    -0.08
    itti
    -0.08
    åīª
    -0.08
    æ´»
    -0.08
    缩
    -0.08
    emony
    -0.08
    lama
    -0.08
    POSITIVE LOGITS
     Bark
    0.10
    寻æ±Ĥ
    0.10
    VERBOSE
    0.09
    ä¸į失
    0.09
    çĶ³è¯·
    0.09
    ibel
    0.09
    çļĦæĦ¿æľĽ
    0.09
    æ¿ł
    0.09
    éĤ¦
    0.09
    ãģ§ãģĻãĤĪãģŃ
    0.08
    Activations Density 0.058%

    No Known Activations