© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7531
    Prev
    Next
    INDEX
    Explanations

    smoothly / easy completion

    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
    วà¸Ļ
    -0.11
    åı¦æľī
    -0.10
    ä½ĵçİ°åĩº
    -0.10
    ä¾Ŀæŧ
    -0.09
    åĢ¼å¾Ĺåħ³æ³¨
    -0.09
    ActionBar
    -0.09
    åĽŀéģ¿
    -0.09
    å¹ķåIJİ
    -0.09
    Dragging
    -0.09
     extinct
    -0.09
    POSITIVE LOGITS
    çĦ¶èĢĮ
    0.14
     Ðŀднако
    0.13
    åį´åıijçİ°
    0.12
     BUT
    0.12
    çļĦç¾İ好
    0.12
    åį´è¢«
    0.11
    没éĹ®é¢ĺ
    0.11
    çĶľç¾İ
    0.11
    ä¸Ģ度
    0.11
     ê·¸ëŁ°ëį°
    0.11
    Activations Density 0.602%

    No Known Activations