© 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. 22920
    Prev
    Next
    INDEX
    Explanations

    can be used

    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
    大ä¼ļ
    -0.10
    è¿Ľä¸ĢæŃ¥
    -0.09
    éĢ²ä¸ĢæŃ¥
    -0.09
    å°½åı¯èĥ½
    -0.09
    esa
    -0.08
    .sdk
    -0.08
    æī¯
    -0.08
    ä¸įæĺİ
    -0.08
     sounding
    -0.08
    orf
    -0.08
    POSITIVE LOGITS
    æī¿åıĹ
    0.12
    人èĦ¸è¯ĨåĪ«
    0.09
    涵çĽĸ
    0.09
    容纳
    0.09
     supports
    0.09
    Themes
    0.09
    åĨ¤
    0.09
     detect
    0.09
    åºĶçĶ¨äºİ
    0.08
     discern
    0.08
    Activations Density 0.153%

    No Known Activations