© 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. 17090
    Prev
    Next
    INDEX
    Explanations

    thinking and remembering

    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
    æĬ¢
    -0.09
    å¼Ħ
    -0.09
    ä¹İ
    -0.09
    èļĿ
    -0.09
    erea
    -0.08
    arpa
    -0.08
    OI
    -0.08
    æĿ¥å®¾
    -0.08
    丧
    -0.08
    åīįæıIJæĺ¯
    -0.08
    POSITIVE LOGITS
    è¿ĩåİ»çļĦ
    0.13
    è¿ĩåİ»
    0.11
    å¾Ģäºĭ
    0.11
    以å¾Ģ
    0.11
    å¦Ĥä½ķ
    0.11
    ãģ®æĸ¹
    0.10
    åīįä¸Ģ天
    0.09
    åīį段æŶéĹ´
    0.09
    æĥ³èµ·
    0.09
    éģİåİ»
    0.09
    Activations Density 0.028%

    No Known Activations