© 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. 40418
    Prev
    Next
    INDEX
    Explanations

    age ranges

    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
    oner
    -0.09
    anth
    -0.09
    æĥł
    -0.09
    ements
    -0.08
    emen
    -0.08
    è¯ķè¡Į
    -0.08
    æ¯ı次éĥ½
    -0.08
    æ¸ħ代
    -0.08
    骤
    -0.08
    ats
    -0.07
    POSITIVE LOGITS
    çļĦæŶåĢĻ
    0.12
    æĹ¶æľŁçļĦ
    0.12
    å°ıæŶåĢĻ
    0.11
    æĹ»
    0.11
    æĹ¶æľŁ
    0.11
    çļĦæĻĤåĢĻ
    0.11
    æľŁ
    0.10
    æŶåĢĻ
    0.10
    ãģ¨ãģįãģ«
    0.10
    adol
    0.10
    Activations Density 0.094%

    No Known Activations