© 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. 16769
    Prev
    Next
    INDEX
    Explanations

    in ... accuracy

    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
    -redux
    -0.11
    åĵ¥
    -0.10
    éĢĢåĩº
    -0.10
    è¾ĩ
    -0.10
    å¯Įæ°ij
    -0.10
    åı£è¢ĭ
    -0.09
    entifier
    -0.09
    _DEFINE
    -0.09
    åħīçݯ
    -0.09
    篦
    -0.09
    POSITIVE LOGITS
    å¿Ĩ
    0.10
    ites
    0.09
    æľªæĪIJ
    0.08
    íĥľ
    0.08
    榴
    0.08
    tero
    0.08
    è§ĦèĮĥ
    0.08
    cul
    0.08
    ekt
    0.08
    ati
    0.08
    Activations Density 0.072%

    No Known Activations