© 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. 58784
    Prev
    Next
    INDEX
    Explanations

    sensory organs and perception

    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
    oming
    -0.10
     Joan
    -0.10
    ä¸ļ
    -0.09
    ewing
    -0.09
    OrCreate
    -0.09
    æŀŀ
    -0.08
    olib
    -0.08
    falls
    -0.08
     recap
    -0.08
     Dover
    -0.08
    POSITIVE LOGITS
    ively
    0.11
    主ä¹īèĢħ
    0.11
    ä¾Ħ
    0.09
    çĽĽå®´
    0.09
    äºĨå¾Īä¹ħ
    0.09
    ìłģìľ¼ë¡ľ
    0.08
    åį£
    0.08
    åįģ足
    0.08
    为ä¸Ģä½ĵ
    0.08
    halb
    0.08
    Activations Density 0.022%

    No Known Activations