© 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. 38527
    Prev
    Next
    INDEX
    Explanations

    Yahoo News, Fantasy, Finance, Travel

    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
    atron
    -0.09
    æŃ¹
    -0.09
    ingle
    -0.09
    éħ¡
    -0.09
    atte
    -0.08
    åıĺåİĭ
    -0.08
    è¡ħ
    -0.08
    rozen
    -0.08
    裹
    -0.08
    åºĦåĽŃ
    -0.08
    POSITIVE LOGITS
     Clem
    0.09
    ç¥ŀåľ£
    0.08
     unpopular
    0.08
    à¹Ģà¸ģ
    0.08
    åħ¶å®ŀæĺ¯
    0.08
    æĮ¤
    0.08
    ogui
    0.08
    åĩĿèģļ
    0.08
    lett
    0.07
    ulp
    0.07
    Activations Density 0.013%

    No Known Activations