© 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. 59170
    Prev
    Next
    INDEX
    Explanations

    Providence, Rhode Island

    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
    çİ°è¡Į
    -0.09
    athon
    -0.09
    ights
    -0.09
    éĩįè¦ģåİŁåĽł
    -0.09
    worm
    -0.08
    ifying
    -0.08
    äºĨ许å¤ļ
    -0.08
    度è¿ĩ
    -0.08
    اد
    -0.08
    æĢĿãģĦ
    -0.08
    POSITIVE LOGITS
    ously
    0.11
    çĴĭ
    0.11
    hue
    0.10
    ally
    0.10
    gar
    0.10
    ection
    0.09
    caling
    0.09
    genesis
    0.09
    iana
    0.09
    ationally
    0.09
    Activations Density 0.005%

    No Known Activations