© 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. 26239
    Prev
    Next
    INDEX
    Explanations

    thinkpad, think tank, thinkbox

    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
    ted
    -0.10
    arily
    -0.09
    locked
    -0.09
    æĻķ
    -0.08
    ting
    -0.08
    asu
    -0.08
    _UNS
    -0.08
    deen
    -0.08
     rtl
    -0.08
    ToList
    -0.08
    POSITIVE LOGITS
    ä»ĭ
    0.12
    elsey
    0.09
     оÑĤд
    0.09
    sgiving
    0.09
    æĪijèĥ½
    0.08
    对çŃĸ
    0.08
    æĴŃ
    0.08
    åīĶ
    0.08
     Boeh
    0.08
    æ¡Į
    0.08
    Activations Density 0.011%

    No Known Activations