© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36229
    Prev
    Next
    INDEX
    Explanations

    years

    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
    ãĤį
    -0.10
    ï¸ı
    -0.10
    úb
    -0.09
    [".
    -0.09
     NOI
    -0.09
    åĤĢ
    -0.08
    è°´
    -0.08
    ãģ¤ãģ®
    -0.08
    衬衫
    -0.08
    alous
    -0.08
    POSITIVE LOGITS
    èĢĮä¸Ķè¿ĺ
    0.10
    åĽ«
    0.08
    æĺ¯æĪij
    0.08
    æIJ
    0.08
    è¿ĻäºĽéĥ½æĺ¯
    0.08
    å°±å¦ĤåIJĮ
    0.08
    .gs
    0.08
    .Xaml
    0.08
    aron
    0.08
    çŁ¥éģĵ
    0.07
    Activations Density 0.183%

    No Known Activations