© 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. 31700
    Prev
    Next
    INDEX
    Explanations

    search and security checks

    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
    æ¯Ļ
    -0.14
    >Delete
    -0.09
    åĪijäºĭ责任
    -0.09
    åıĤä¸İ
    -0.09
    临
    -0.09
    æµ·å²Ľ
    -0.09
    绣çŃ¹
    -0.09
    åıį对
    -0.09
    ä¾į
    -0.09
    åıĥèĪĩ
    -0.08
    POSITIVE LOGITS
    æIJľ
    0.15
    æ£ĢæŁ¥
    0.11
     search
    0.10
     ê²Ģ
    0.10
    search
    0.10
    æIJľç´¢
    0.10
    æİı
    0.10
    æª¢æŁ¥
    0.10
    -search
    0.10
     searching
    0.10
    Activations Density 0.072%

    No Known Activations