© 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. 36355
    Prev
    Next
    INDEX
    Explanations

    rings or Leap.Unity

    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
    anno
    -0.09
    èŀį
    -0.09
    çijĻ
    -0.08
    è·Łéļı
    -0.08
    itag
    -0.08
    éĻį
    -0.08
    追赶
    -0.08
    票
    -0.08
    æĸĹ
    -0.08
    æĹĸ
    -0.08
    POSITIVE LOGITS
    æĮĩå°ĸ
    0.12
    æı¡ä½ı
    0.11
    æı¡æīĭ
    0.11
    æĭ³å¤´
    0.10
    å³Ļ
    0.10
    ä¸Ģç¢Ĺ
    0.10
    æīĭæİĮ
    0.10
    ä¸Ģæīĭ
    0.10
    æīĭä¸Ĭ
    0.09
    æĺ¯ä¸Ģ座
    0.09
    Activations Density 0.070%

    No Known Activations