© 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. 8363
    Prev
    Next
    INDEX
    Explanations

    access and flexibility

    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
    lasses
    -0.09
    .opt
    -0.09
    æį¢äºĨ
    -0.08
    åºŁå¼ĥ
    -0.08
    ä¸ĩ象
    -0.08
    леÑĩ
    -0.08
    æĢģ度
    -0.08
    åijĬè¯īä»ĸ
    -0.08
    ilot
    -0.08
    æ´Ĺè¡£
    -0.08
    POSITIVE LOGITS
    çļĦæľºä¼ļ
    0.11
    æ©Łæľĥ
    0.09
    ĪæĿĥ
    0.09
    èĥ½åģļåĪ°
    0.09
    anst
    0.09
    æľºä¼ļ
    0.09
    yyy
    0.08
    ìĭľê°Ħ
    0.08
     access
    0.08
    æIJŃ
    0.08
    Activations Density 0.010%

    No Known Activations