© 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. 48722
    Prev
    Next
    INDEX
    Explanations

    née surname

    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
    ilton
    -0.11
    çĭłæĬĵ
    -0.09
    为æĬĵ
    -0.09
    æīĭæĦŁ
    -0.09
    æıĸ
    -0.09
    ä¸įæĩĪ
    -0.09
    楼ä¸Ĭ
    -0.08
    ä¸Ģæŀ¶
    -0.08
    éĺµèIJ¥
    -0.08
    erson
    -0.08
    POSITIVE LOGITS
    ายà¸Ļ
    0.09
    è·³åĩº
    0.08
    å¼Ħ
    0.08
     Yapı
    0.08
    ëŀĢ
    0.08
    insula
    0.08
    \Page
    0.08
    梧
    0.08
    /AP
    0.08
     Marcos
    0.08
    Activations Density 0.016%

    No Known Activations