© 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. 37037
    Prev
    Next
    INDEX
    Explanations

    ale or female measurements

    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
    çĭĹ
    -0.10
    ãĤ¤ãĥĻ
    -0.09
    ä¸į失
    -0.09
    æ±¹
    -0.09
     Gin
    -0.09
    åĨ³çŃĸ
    -0.09
    fal
    -0.09
    acen
    -0.08
    çĨĺ
    -0.08
     Ethi
    -0.08
    POSITIVE LOGITS
    èĽĻ
    0.11
     frog
    0.09
    湿
    0.09
    ROC
    0.09
    èĻĴ
    0.08
    æ½ĭ
    0.08
    åħ¬çĽĬæĢ§
    0.08
    æłĸ
    0.08
    çĪ¬
    0.08
    æ²ĩ
    0.08
    Activations Density 0.075%

    No Known Activations