© 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. 9058
    Prev
    Next
    INDEX
    Explanations

    James Haley or names like James+last name

    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
    åīįæīĢ
    -0.11
    uring
    -0.11
    abel
    -0.10
    ย
    -0.10
    ital
    -0.10
    ively
    -0.10
    ëĭĿ
    -0.09
    èĩ¾
    -0.09
    æ°Ľ
    -0.09
    ius
    -0.09
    POSITIVE LOGITS
    -sama
    0.12
    ãĥ³ãĤ°
    0.11
    ëģĶ
    0.11
    综
    0.10
    ãĤĪãģĨãģª
    0.09
    ouflage
    0.09
    ب
    0.09
    воÑĢ
    0.09
    InChildren
    0.09
    IJ
    0.09
    Activations Density 0.034%

    No Known Activations