© 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. 53064
    Prev
    Next
    INDEX
    Explanations

    polysaccharide-degrading

    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
    åIJİèĢħ
    -0.10
    è¿Ħ
    -0.10
    çŃ®
    -0.09
    èĤī
    -0.09
    è¿ĩå¾Ĺ
    -0.08
    æĢİä¹ĪåĽŀäºĭ
    -0.08
    æĶ¿æĿĥ
    -0.08
    mand
    -0.08
    ä¸ĵå±ŀ
    -0.08
    èĢĥçĤ¹
    -0.08
    POSITIVE LOGITS
    åºŀ大
    0.10
    ivas
    0.09
    å®ı大
    0.09
    èĮ«èĮ«
    0.09
    çģ¯ç¬¼
    0.09
    cloth
    0.08
    太大
    0.08
    ä»İä¸Ń
    0.08
    erie
    0.08
     Devils
    0.08
    Activations Density 0.239%

    No Known Activations