© 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. 60625
    Prev
    Next
    INDEX
    Explanations

    drummer, drum, banneret, piper

    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
    æijĦ
    -0.10
    ä¹Ķ
    -0.10
    æĭ±
    -0.09
    Ñģел
    -0.09
    å¾ĭå¸Ī
    -0.09
    äter
    -0.09
    篱
    -0.09
    æıĨ
    -0.09
    lify
    -0.09
    iej
    -0.08
    POSITIVE LOGITS
    é¼ĵ
    0.11
    ä½ĺ
    0.10
     drum
    0.10
    signal
    0.09
     drums
    0.09
    åĴļ
    0.09
    éĥ¨éĺŁ
    0.09
    è¡Ģåİĭ
    0.09
    éĶ£
    0.08
    失
    0.08
    Activations Density 0.092%

    No Known Activations