© 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. 20470
    Prev
    Next
    INDEX
    Explanations

    Neor, Phom, Callor, Dremiss, Microt

    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
    пÑĥÑĤ
    -0.10
    èĥİ
    -0.09
    ccoli
    -0.09
     Herz
    -0.08
    æŁĵ
    -0.08
    æľ½
    -0.08
    家çĶ¨
    -0.08
    ÑĦон
    -0.08
    conomy
    -0.08
    çĻ½è¡£
    -0.08
    POSITIVE LOGITS
    ÙĬات
    0.09
    端æŃ£
    0.09
    çĿ¦
    0.08
    ä¸Ģç§į
    0.08
     allied
    0.08
    ãĥ¡ãĥª
    0.08
    Ìģ
    0.08
    ä¼ĺæĥł
    0.08
    åĨį说
    0.08
     Nep
    0.08
    Activations Density 0.338%

    No Known Activations