© 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. 12372
    Prev
    Next
    INDEX
    Explanations

    it is

    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
    theless
    -0.10
    ESIS
    -0.10
    út
    -0.10
    holds
    -0.09
    å¾Ĺå¾Ī
    -0.09
    ously
    -0.09
    haft
    -0.09
    ãģĤãĤĭç¨ĭ度
    -0.09
    ãģĵãģ¨ãģĮãģ§ãģįãĤĭ
    -0.09
    ÑģÑĮ
    -0.09
    POSITIVE LOGITS
    inerary
    0.14
    èĢģ人家
    0.14
    /th
    0.14
    unes
    0.12
    iner
    0.11
    зв
    0.11
    izen
    0.11
    otal
    0.11
    oretical
    0.11
    self
    0.11
    Activations Density 0.467%

    No Known Activations