© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61218
    Prev
    Next
    INDEX
    Explanations

    sender and recipient email addresses

    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
    纶
    -0.10
    æŀľæĸŃ
    -0.09
    åĻ¨æ¢°
    -0.09
    istine
    -0.09
    æī«çłģ
    -0.09
    è¿ĽéŨ
    -0.08
     artyku
    -0.08
    åķľ
    -0.08
    åĻ¨åħ·
    -0.08
    éŀ
    -0.08
    POSITIVE LOGITS
    ä¿¡
    0.15
    éĤ®ä»¶
    0.14
    sender
    0.13
     sender
    0.12
    ä¸Ģå°ģ
    0.12
    åĽŀå¤į
    0.11
     email
    0.11
    âľī
    0.11
     Sender
    0.11
     Email
    0.10
    Activations Density 0.309%

    No Known Activations