© 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. 24150
    Prev
    Next
    INDEX
    Explanations

    geometric properties and operations

    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
    spot
    -0.10
    à²ł
    -0.09
    ä¸ĢèĤ¡
    -0.09
    èį¥
    -0.09
    äºĭä¸ļåıijå±ķ
    -0.08
    å¦Ĥå®ŀ
    -0.08
    liable
    -0.08
    atory
    -0.08
    åĴĮåľ°åĮº
    -0.08
    纣
    -0.08
    POSITIVE LOGITS
    çĻĸ
    0.11
    ally
    0.11
    é¦ĸæī¹
    0.09
    -minded
    0.09
    /met
    0.09
    åŃ¦å®¶
    0.09
    ities
    0.09
    ians
    0.09
    rical
    0.08
    (geometry
    0.08
    Activations Density 0.063%

    No Known Activations