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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36932
    Prev
    Next
    INDEX
    Explanations

    Championships and tournaments

    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
    åı¦
    -0.10
    çŁ¥éģĵäºĨ
    -0.08
    TAG
    -0.08
    éĺį
    -0.08
    à¹ģฮ
    -0.08
    奥æĸ¯åį¡
    -0.08
    èݪ
    -0.08
    è¾ĵäºĨ
    -0.08
    enticator
    -0.08
    .transparent
    -0.08
    POSITIVE LOGITS
    äºĭå®ľ
    0.09
    ä¸ĵåĮº
    0.08
    èķ²
    0.08
    ibern
    0.08
    ä¼Ļ
    0.08
     Wheeler
    0.08
    ãĥªãĥ³ãĤ°
    0.08
    à¹Ĥà¸Ľà¸£à¹ģà¸ģรม
    0.08
    åIJĪä½ľåħ³ç³»
    0.08
    èł¢
    0.08
    Activations Density 0.008%

    No Known Activations