© 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. 1311
    Prev
    Next
    INDEX
    Explanations

    HS, US, us abbreviations

    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
    -chain
    -0.09
     blocker
    -0.08
    æĹ¶ä»£ä¸ŃåĽ½
    -0.08
    Ø®ÙĦÙģ
    -0.08
    åij¨è½¬
    -0.08
    çŃĸ
    -0.08
    è»
    -0.08
    2
    -0.08
    6
    -0.08
    è¿ŀéĶģ
    -0.08
    POSITIVE LOGITS
    ÙĬات
    0.09
    strain
    0.08
    irected
    0.08
    éĤ£è¾¹
    0.08
    wich
    0.08
    è°ĥæŁ¥æĺ¾ç¤º
    0.08
    å¿«æĬ¥
    0.08
    ãĥ¢ãĥİ
    0.08
    åij
    0.08
    èĤ
    0.08
    Activations Density 0.002%

    No Known Activations