© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35894
    Prev
    Next
    INDEX
    Explanations

    after or following

    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
    æĿ¥åĽŀ
    -0.12
    ãģĵãĤĮãģĭãĤī
    -0.10
     lúc
    -0.10
    åĪ°æŶåĢĻ
    -0.10
    owe
    -0.09
    è¿ĻæŶåĢĻ
    -0.09
    æѤæŶ
    -0.09
    å½ĵåĪĿ
    -0.09
    å½ĵå¹´
    -0.09
    è¿Ł
    -0.09
    POSITIVE LOGITS
    ä¸įä¹ħ
    0.14
    æīįåıijçİ°
    0.14
    wards
    0.13
    (after
    0.13
     Ùħباشرة
    0.13
    æīįçŁ¥éģĵ
    0.12
    å¾Īä¹ħ
    0.11
    noon
    0.11
    ward
    0.11
    WARDS
    0.11
    Activations Density 0.106%

    No Known Activations