© 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. 26414
    Prev
    Next
    INDEX
    Explanations

    fitted with

    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
    Not in Any Lists

    No Comments

    Negative Logits
    fulness
    -0.11
    fully
    -0.10
    ward
    -0.09
    ifying
    -0.09
    ão
    -0.09
     bare
    -0.09
    ä¸Ģåı£æ°Ķ
    -0.08
    hound
    -0.08
    WARD
    -0.08
    ken
    -0.08
    POSITIVE LOGITS
    离éĢĢä¼ij
    0.09
    ÑĥлÑĮ
    0.09
    icious
    0.09
    ised
    0.09
    ULD
    0.09
    aggio
    0.08
     Elli
    0.08
    CONF
    0.08
    ngr
    0.08
    ISED
    0.08
    Activations Density 0.012%

    No Known Activations