© 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. 24095
    Prev
    Next
    INDEX
    Explanations

    synthesis of

    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
    liness
    -0.10
    PEC
    -0.09
    对åŃ©åŃIJ
    -0.09
    adius
    -0.09
    esting
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.09
    agna
    -0.09
    ×ķת
    -0.08
    untime
    -0.08
    adesh
    -0.08
    POSITIVE LOGITS
    thetic
    0.13
    enade
    0.10
    esthetic
    0.10
    apses
    0.09
    onyms
    0.09
    onymous
    0.09
    åĭĥåĭĥ
    0.09
    боÑĢ
    0.09
    odont
    0.09
    encer
    0.09
    Activations Density 0.078%

    No Known Activations