© 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. 16712
    Prev
    Next
    INDEX
    Explanations

    list_1 AND list_2

    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
    åijĹ
    -0.11
    麻
    -0.10
    çĻ¾å®¶
    -0.10
     опиÑģание
    -0.10
    ำ
    -0.10
    itel
    -0.09
    ittel
    -0.09
    åĩĽ
    -0.09
    ä¸ĩ象
    -0.09
    ä¿ĥ使
    -0.09
    POSITIVE LOGITS
    -West
    0.08
    _SOFT
    0.08
     compos
    0.08
    paces
    0.07
    oks
    0.07
     tù
    0.07
    ä»Ĺ
    0.07
    erk
    0.07
    -prof
    0.07
     ±
    0.07
    Activations Density 0.069%

    No Known Activations