© 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. 35589
    Prev
    Next
    INDEX
    Explanations

    have been

    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
     weakest
    -0.08
    aus
    -0.08
    亵
    -0.08
    èģ
    -0.08
    èį«
    -0.08
    à¹Ģà¸ī
    -0.08
    indy
    -0.08
     Jacqueline
    -0.08
    çļĦè§ĤçĤ¹
    -0.08
    å±ı
    -0.08
    POSITIVE LOGITS
    ä¸ĢéĹª
    0.10
    è¾¾åĪ°
    0.10
    æĭ¿åĪ°
    0.09
    泯
    0.09
    åİ»è¿ĩ
    0.09
    èĩ»
    0.09
    çªģçł´
    0.09
    ä½İäºİ
    0.09
    éĢ¾
    0.09
    /top
    0.09
    Activations Density 0.094%

    No Known Activations