© 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. 3102
    Prev
    Next
    INDEX
    Explanations

    Reed and names ending in 'ed' or 'ied'

    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
    ially
    -0.10
     же
    -0.10
    Ĺ
    -0.10
    itics
    -0.10
    ï¸ı
    -0.09
    anger
    -0.09
    ä¸ĢåĽŀäºĭ
    -0.09
    brew
    -0.09
    ä¸Ģåľº
    -0.09
    ials
    -0.08
    POSITIVE LOGITS
    iness
    0.13
    edly
    0.12
    оÑĢ
    0.12
    hardt
    0.11
    lessly
    0.10
    sville
    0.10
    ãģĹãģ¾
    0.10
    vertise
    0.10
    iculty
    0.09
    èĥ½æī¾åĪ°
    0.09
    Activations Density 0.005%

    No Known Activations