© 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. 7389
    Prev
    Next
    INDEX
    Explanations

    Android storage paths

    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¸Ģæ³¢
    -0.10
    ä¸Ģéģį
    -0.10
    æ¿Ģ
    -0.09
    æĵĬ
    -0.09
    äºĨä¸Ģéģį
    -0.09
    agues
    -0.09
    åı¯ä¿¡
    -0.09
    年轻人
    -0.09
    éĴŁ
    -0.08
    chn
    -0.08
    POSITIVE LOGITS
    ORITY
    0.09
    Toggle
    0.09
    äº¤æĽ¿
    0.09
    åĽ½åľŁ
    0.08
     Baylor
    0.08
    Bat
    0.08
     ipad
    0.08
    å°ķ
    0.08
    æİĪäºĪ
    0.08
     IOS
    0.08
    Activations Density 0.117%

    No Known Activations