© 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. 57341
    Prev
    Next
    INDEX
    Explanations

    prizes and offers

    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
    èŁĭ
    -0.08
    çĨŁæĤīçļĦ
    -0.08
    åģļå¾Ĺ
    -0.08
     meetings
    -0.08
    4
    -0.08
    æįº
    -0.08
    åģľçķĻ
    -0.07
     tÃłn
    -0.07
    èĭĽ
    -0.07
    3
    -0.07
    POSITIVE LOGITS
    å®ŀçī©
    0.12
    ç»Ļ大家
    0.12
    æ¯ı人
    0.12
    æ¯ıä½į
    0.12
    èµł
    0.11
    礼çī©
    0.11
    大家ä¸Ģèµ·
    0.11
    ä»·åĢ¼
    0.11
    大家
    0.11
    åıijæĶ¾
    0.10
    Activations Density 0.034%

    No Known Activations