© 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. 38726
    Prev
    Next
    INDEX
    Explanations

    poles and posts

    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
    å¼ĢéŨ
    -0.09
    轨迹
    -0.09
    è¸
    -0.09
    adius
    -0.09
    åĬŀ
    -0.09
     sÃłn
    -0.09
    è·µè¡Į
    -0.09
    å¯ĵ
    -0.08
    æİ¥åĬĽ
    -0.08
    å¼ĺ
    -0.08
    POSITIVE LOGITS
    è·¯çģ¯
    0.16
    åŀĥåľ¾æ¡¶
    0.13
    èĢIJçĶ¨
    0.10
    åħ¬åħ±èµĦæºIJ
    0.10
    ä¿¡ç®±
    0.10
    çģ¯ç¬¼
    0.10
    çģ¯
    0.10
    社ä¼ļæ²»çIJĨ
    0.10
    å¸ĤæĶ¿
    0.10
    è¡Ĺ头
    0.10
    Activations Density 0.090%

    No Known Activations