© 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. 775
    Prev
    Next
    INDEX
    Explanations

    cumin, turmeric, cinnamon, spices

    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
    ests
    -0.10
    iefs
    -0.10
     Manitoba
    -0.09
    äºĽä»Ģä¹Ī
    -0.09
    æ°ª
    -0.09
    ç¦Ħ
    -0.09
    æĿŁ
    -0.09
    å±ħçĦ¶
    -0.08
    管çIJĨä¸Ńå¿ĥ
    -0.08
    OTH
    -0.08
    POSITIVE LOGITS
    æŁģ
    0.09
    chio
    0.09
    SY
    0.08
    allee
    0.08
    éģij
    0.08
    otel
    0.08
    ris
    0.08
    ikk
    0.08
    çĶµåĻ¨
    0.08
    _ASSUME
    0.07
    Activations Density 0.011%

    No Known Activations