© 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. 52825
    Prev
    Next
    INDEX
    Explanations

    grand jury deliberations

    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
    øj
    -0.09
    祸
    -0.09
    æŀ¸
    -0.08
    ORN
    -0.08
    ç¥Ĺ
    -0.08
    çĪ½
    -0.08
    æľĢ大çļĦ
    -0.08
    ë¡ł
    -0.08
     visa
    -0.08
    åħĢ
    -0.08
    POSITIVE LOGITS
    éĦ¢
    0.10
     Sunderland
    0.09
    hart
    0.09
    ä½Ł
    0.09
    erus
    0.09
    人æĢ§
    0.09
    æ¿¡
    0.08
     runway
    0.08
    å¾Ń
    0.08
    åĽ½å®¶éĩįçĤ¹
    0.08
    Activations Density 0.076%

    No Known Activations