© 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. 24024
    Prev
    Next
    INDEX
    Explanations

    tolerance and tolerability

    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
    resse
    -0.09
    åIJĮæĦı
    -0.08
    manship
    -0.08
    elman
    -0.08
    otle
    -0.08
    交代
    -0.08
    isle
    -0.08
    ness
    -0.08
    ilan
    -0.08
    佬
    -0.08
    POSITIVE LOGITS
    ably
    0.17
    åĴĮæĶ¯æĮģ
    0.12
    çĹĩ
    0.11
    ANCE
    0.11
    anz
    0.11
    ances
    0.11
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    0.10
    à¸ģารà¸Ĺำ
    0.10
    IBLE
    0.10
    à¸ģาร
    0.10
    Activations Density 0.018%

    No Known Activations