© 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. 21833
    Prev
    Next
    INDEX
    Explanations

    include / mention

    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
    ä»ŀ
    -0.09
    ðŁĴ¯
    -0.09
    eree
    -0.09
    ç¥ī
    -0.09
    çĢijå¸ĥ
    -0.08
    خاص
    -0.08
    çĵ
    -0.08
    REEN
    -0.08
    æĶ¯éħį
    -0.08
    utral
    -0.08
    POSITIVE LOGITS
    注æĺİæĿ¥æºIJ
    0.11
    æłĩæĺİ
    0.11
    注æĺİ
    0.10
    åĨł
    0.10
    å¤ĩ注
    0.10
     ТÑĥÑĢ
    0.09
     mention
    0.09
    éĻĦ
    0.09
    åıĹ伤
    0.09
     kèm
    0.09
    Activations Density 0.198%

    No Known Activations