© 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. 63824
    Prev
    Next
    INDEX
    Explanations

    part, separate, split

    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
    åĨ¢
    -0.10
    çĦĻ
    -0.10
    olist
    -0.10
    utt
    -0.09
    bble
    -0.08
    åı¯ä»¥æĬĬ
    -0.08
    ãĥ¼ãĤ¿
    -0.08
    èĩªåıij
    -0.08
    -nil
    -0.08
    kie
    -0.08
    POSITIVE LOGITS
    çĿ½
    0.09
    åĪĨå¼Ģ
    0.08
    å¨ħ
    0.08
    éŸ
    0.08
    quan
    0.08
    çīŁ
    0.08
    ight
    0.08
    nable
    0.08
    alia
    0.08
     stro
    0.08
    Activations Density 0.004%

    No Known Activations