© 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. 31204
    Prev
    Next
    INDEX
    Explanations

    events happening soon

    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
    æĹ¥åIJİ
    -0.10
    å½ĵæŶ
    -0.10
    èĽ®
    -0.10
    ä¸Ģè¾ĪåŃIJ
    -0.10
    å¿
    -0.09
    个åĪ«
    -0.09
    äºĭåIJİ
    -0.09
    8
    -0.09
    1
    -0.09
    äºĨåįĬ天
    -0.09
    POSITIVE LOGITS
    möglich
    0.10
     gá»įn
    0.09
    çķ¿
    0.09
    宣åijĬ
    0.09
    åĬ¨å·¥
    0.09
    宣å¸ĥ
    0.09
    ä¸įä¹ħ
    0.09
    ç·ļä¸Ĭ
    0.08
    ész
    0.08
    æĸĹå¿Ĺ
    0.08
    Activations Density 0.026%

    No Known Activations