© 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. 40171
    Prev
    Next
    INDEX
    Explanations

    map or map of

    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
    ongo
    -0.09
     Cair
    -0.09
    å°¼æĸ¯
    -0.08
     Civ
    -0.08
    ино
    -0.08
    æĿIJ
    -0.08
    çĭĻ
    -0.08
    èĭ
    -0.08
    orns
    -0.08
    ONGO
    -0.08
    POSITIVE LOGITS
    åľ°åĽ¾
    0.12
    æĸ¹ä½į
    0.10
    çļĦåľ°åĽ¾
    0.10
    .getMap
    0.10
    路线
    0.10
    åľ°çIJĨä½įç½®
    0.10
    é¬
    0.10
    è¿IJè´¹
    0.09
    ä½įç½®
    0.09
    lope
    0.09
    Activations Density 0.022%

    No Known Activations