© 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. 32587
    Prev
    Next
    INDEX
    Explanations

    If you

    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
     Äijâu
    -0.11
    åijĬè¯ī大家
    -0.11
    ç¾İè²Į
    -0.10
    éļ¾éģĵ
    -0.10
    è¦ģä¹Ī
    -0.10
    ennie
    -0.10
    èĢģ人家
    -0.10
    åijĬè¯ī她
    -0.09
    æ¼Ĥ亮
    -0.09
    andin
    -0.09
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.09
    æľīå¿ħè¦ģ
    0.09
    å¿ħè¦ģ
    0.09
    å®ŀåľ¨
    0.08
    å¤ļ次
    0.08
    ibbon
    0.08
    æľīå¤ļ
    0.08
    rah
    0.08
    æł·
    0.08
    æĬĺ
    0.08
    Activations Density 0.046%

    No Known Activations