© 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. 9480
    Prev
    Next
    INDEX
    Explanations

    conversation and discussion

    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
    èģĶåIJĪä¼ļ
    -0.09
    è·¡
    -0.09
    æĻ°
    -0.08
    _Copy
    -0.08
    æľīä¸Ģ天
    -0.08
     min
    -0.08
    çĹķ迹
    -0.08
    çĦ¶æĺ¯
    -0.08
    min
    -0.08
    _fac
    -0.08
    POSITIVE LOGITS
    åīĸ
    0.10
    à¹Īม
    0.09
    åĨĮ
    0.08
    è¯Ŀé¢ĺ
    0.08
    _THREAD
    0.08
    æĸ¯çī¹
    0.08
    SETS
    0.08
    ÑĤоÑĢ
    0.08
    entic
    0.08
    ä¸Ģè´¯
    0.08
    Activations Density 0.011%

    No Known Activations