© 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. 58330
    Prev
    Next
    INDEX
    Explanations

    appellate court proceedings

    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
    审çIJĨ
    -0.11
    olley
    -0.10
    象å¾ģ
    -0.10
    æ¶īæ¡Ī
    -0.10
    åıijåĩº
    -0.09
    ERA
    -0.09
    æ³ķå®ĺ
    -0.09
    ç§ī
    -0.09
    ä¸ĭ鼨
    -0.09
    è£ģåĪ¤
    -0.09
    POSITIVE LOGITS
    ç¦ģ
    0.10
    ç¿ķ
    0.10
    çĶŁçĶŁ
    0.10
     ÑģлÑĥж
    0.09
    èįŁ
    0.09
    åĬŃ
    0.09
    飶
    0.09
    ÑģÑħ
    0.09
    ç»Ń
    0.09
    ä¿Ŀä¿®
    0.08
    Activations Density 0.440%

    No Known Activations