© 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. 7173
    Prev
    Next
    INDEX
    Explanations

    applicable law

    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
    ä¼ļåIJĮ
    -0.10
     пиÑĤаниÑı
    -0.08
    详æĥħ
    -0.08
    çī¹ä»·
    -0.08
    èµĤ
    -0.08
    éĶĢåĶ®æ¸łéģĵ
    -0.08
    尾巴
    -0.08
    éĥ¢
    -0.08
    èĦ¯
    -0.08
    sr
    -0.08
    POSITIVE LOGITS
    nable
    0.11
    çĿĢä»ĸ
    0.10
    оÑĤоÑĢ
    0.09
    äºĮ线
    0.09
    uable
    0.09
    aisy
    0.09
    anners
    0.09
    /all
    0.09
    ableObject
    0.09
    æį¢
    0.09
    Activations Density 0.020%

    No Known Activations