© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39858
    Prev
    Next
    INDEX
    Explanations

    android API versions

    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
    ä¸įè§ģäºĨ
    -0.10
    主ä¸ļ
    -0.10
    WSC
    -0.09
    æ®Ĩ
    -0.09
     Phelps
    -0.09
    çļĦæĥ³æ³ķ
    -0.09
    amazon
    -0.09
    äºĺ
    -0.09
     NONINFRINGEMENT
    -0.09
    æĶ¾åѦ
    -0.09
    POSITIVE LOGITS
    .OS
    0.09
    .pivot
    0.09
    (OS
    0.09
     Bench
    0.09
    åħ¼
    0.08
    eo
    0.08
    TextEdit
    0.08
    次
    0.08
    æĵįä½ľç³»ç»Ł
    0.08
     bat
    0.08
    Activations Density 0.056%

    No Known Activations