© 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. 60578
    Prev
    Next
    INDEX
    Explanations

    clay tile, brick, articles

    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
    éĢĭ
    -0.10
    å±
    -0.09
    .ds
    -0.09
    olen
    -0.09
    æĹı
    -0.08
    lama
    -0.08
    éĺª
    -0.08
    å§Ķæīĺ
    -0.08
    onne
    -0.08
    _configuration
    -0.08
    POSITIVE LOGITS
    çłĸ
    0.12
    çĥ§
    0.10
    çĩĴ
    0.10
    æ³¥åľŁ
    0.10
    CHIP
    0.10
     brick
    0.09
     Brick
    0.09
    墼
    0.09
    æ³¥
    0.09
    çª
    0.09
    Activations Density 0.037%

    No Known Activations