© 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. 34910
    Prev
    Next
    INDEX
    Explanations

    computer aided design

    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
    ä¸ij
    -0.09
    æĥŁ
    -0.09
    åľ©
    -0.09
     Vulcan
    -0.08
    éŨæĪ·ç½ijç«Ļ
    -0.08
    ÑĩаÑĤ
    -0.08
    åĿł
    -0.08
    éĻĪè¿°
    -0.08
    isko
    -0.08
    ertain
    -0.08
    POSITIVE LOGITS
    ç¼°
    0.10
    tor
    0.09
    AYS
    0.09
    visor
    0.09
    缪
    0.08
    åĽ¾çº¸
    0.08
    ä¸īå±Ĥ
    0.08
    夫
    0.08
    å·´åŁº
    0.08
    discount
    0.08
    Activations Density 0.033%

    No Known Activations