© 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. 19266
    Prev
    Next
    INDEX
    Explanations

    who clauses

    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
    å¦Ĥæľīä¾µæĿĥ
    -0.12
    éļıæŶ
    -0.11
    éļ¨æĻĤ
    -0.11
    èĢģçĪ·åŃIJ
    -0.11
    æīįçŁ¥éģĵ
    -0.11
    å½ĵä½ľ
    -0.10
    è°ģçŁ¥
    -0.10
    å½ĵä¹ĭæĹłæĦ§
    -0.10
    è¦ģä¹Ī
    -0.10
    æģ»
    -0.09
    POSITIVE LOGITS
    说æĺ¯
    0.08
    èµ¢å¾Ĺ
    0.08
    æ»ŀ
    0.08
    ä¸įæħİ
    0.08
    åĩºçİ°
    0.08
     Fac
    0.08
    çĥĺ
    0.08
    rox
    0.08
    \/
    0.08
    ients
    0.08
    Activations Density 0.071%

    No Known Activations