© 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. 36716
    Prev
    Next
    INDEX
    Explanations

    expresses positive sentiment

    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
    åĽ°æī°
    -0.10
    gren
    -0.08
    è¡¡éĩı
    -0.08
     Od
    -0.08
    odb
    -0.08
    æĶ¾åģĩ
    -0.08
     Cord
    -0.08
    SPAN
    -0.08
    æIJģ
    -0.08
    æĶ¾å®½
    -0.08
    POSITIVE LOGITS
    æĹłæ¯Ķ
    0.11
    èį£å¹¸
    0.10
    iona
    0.10
    åºĨ幸
    0.10
    æħ¢
    0.10
    ä¸ĩåĪĨ
    0.10
    CLK
    0.09
    hof
    0.09
    ulg
    0.09
    欣æħ°
    0.09
    Activations Density 0.049%

    No Known Activations