© 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. 63974
    Prev
    Next
    INDEX
    Explanations

    camera brands and software

    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
    ä¸įçĦ¶
    -0.13
    estre
    -0.09
    iron
    -0.09
    uation
    -0.08
    ç½²
    -0.08
    ird
    -0.08
    ص
    -0.08
     curt
    -0.08
     Banc
    -0.08
    èĩ¾
    -0.08
    POSITIVE LOGITS
    人éĥ½
    0.10
    IZER
    0.09
    oses
    0.09
    ians
    0.09
    å®īåİ¿
    0.09
    ied
    0.09
    åĢļ
    0.08
    ÑģеÑĤ
    0.08
    aira
    0.08
    osoph
    0.08
    Activations Density 0.004%

    No Known Activations