© 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. 50765
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
    å¥ł
    -0.10
    irts
    -0.10
    碰
    -0.10
    æłī
    -0.10
    owan
    -0.10
    çIJĨæĥ³çļĦ
    -0.09
    å®ļçĤ¹
    -0.09
    æĬ±
    -0.09
    zers
    -0.09
    usters
    -0.09
    POSITIVE LOGITS
    еÑĨ
    0.10
    è¿Ļä¹Łæĺ¯
    0.10
    å¤ļåľ°
    0.09
    scape
    0.09
    èĬ±èįī
    0.08
    å¿Ĵ
    0.08
     XX
    0.08
    ä¸Ŀ
    0.08
    çī¯
    0.08
    croft
    0.08
    Activations Density 0.037%

    No Known Activations