© 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. 16928
    Prev
    Next
    INDEX
    Explanations

    online discussion forums

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çŁ³æ¦´
    -0.10
    é£ĵ
    -0.09
    åħ³éŨ
    -0.09
     clubhouse
    -0.08
     Graves
    -0.08
    æ¶Īè´¹åĵģ
    -0.08
    /GPL
    -0.08
    linger
    -0.08
    å½±çīĩ
    -0.08
    éĥ½è¯´
    -0.08
    POSITIVE LOGITS
    è¿Ļ群
    0.09
    å°ijè§ģ
    0.09
    æľĢå°ij
    0.08
    讯
    0.08
    иж
    0.08
     Rut
    0.08
    æĺ¾éľ²
    0.08
    åįıå®ļ
    0.08
    å¾Īå°ij
    0.08
     Larson
    0.08
    Activations Density 0.098%

    No Known Activations