© 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. 6774
    Prev
    Next
    INDEX
    Explanations

    grip, statement, roll, stage, oasis

    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
    æĺİæľĹ
    -0.09
     lot
    -0.09
    æĺŃ
    -0.08
    illian
    -0.08
    å¥
    -0.08
    广éĺĶçļĦ
    -0.08
    nim
    -0.08
    æĺİæĻ°
    -0.08
    ariat
    -0.08
    lesc
    -0.08
    POSITIVE LOGITS
    æIJĵ
    0.10
    wick
    0.10
    è¡Ķ
    0.10
    çħĻ
    0.09
    å°ıé¢Ŀ贷款
    0.09
    æįı
    0.09
     Dur
    0.09
    嫦
    0.09
    å¯Ĵ
    0.09
    åłµ
    0.09
    Activations Density 0.027%

    No Known Activations