© 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. 16723
    Prev
    Next
    INDEX
    Explanations

    professional roles or actions

    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
    ees
    -0.10
    ä¸įåħĭ
    -0.09
    çªŁ
    -0.09
    ampler
    -0.08
     unlocked
    -0.08
     покÑĥп
    -0.08
    åį¸
    -0.08
    ëŁ¼
    -0.08
    íķĺìĭľ
    -0.07
     Locked
    -0.07
    POSITIVE LOGITS
    è£ģåĪ¤
    0.16
    åħ¨åľº
    0.12
    èµĽåIJİ
    0.11
    æī§æ³ķ
    0.11
    æľ¬åľºæ¯ĶèµĽ
    0.11
    è§ĦåĪĻ
    0.11
    è£ģå®ļ
    0.10
    çĬ¯è§Ħ
    0.10
    尺度
    0.10
     çĻ»
    0.10
    Activations Density 0.082%

    No Known Activations