© 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. 52158
    Prev
    Next
    INDEX
    Explanations

    action verbs leading to a result

    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
    ä¹ŁæĽ¾
    -0.10
    á¸Ĭ
    -0.09
    å¾Įä¾Ĩ
    -0.09
    æĹ©å°±
    -0.09
    åIJİæĿ¥
    -0.08
    verts
    -0.08
    åģļè¿ĩ
    -0.08
    nah
    -0.08
    æĽ¾
    -0.08
    æħ¢
    -0.08
    POSITIVE LOGITS
    对æĪij们
    0.10
    æĪijéĻ¢
    0.10
    åĩij
    0.09
    è¿ĺä¸įæĺ¯
    0.09
    Refreshing
    0.09
    æĪijæł¡
    0.09
    åīįæīĢ
    0.09
    ç¼±
    0.08
    æĥĨ
    0.08
    å®ĮåĸĦ
    0.08
    Activations Density 0.083%

    No Known Activations