© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51687
    Prev
    Next
    INDEX
    Explanations

    invest in

    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
    移æ¤į
    -0.11
    亲åĪĩ
    -0.10
    imers
    -0.10
    æ²Ĵ
    -0.10
    dling
    -0.10
    çĦ¦çĤ¹
    -0.09
     ëĤĺëĬĶ
    -0.09
    eteor
    -0.09
    alytics
    -0.09
    éĢ®
    -0.09
    POSITIVE LOGITS
    èĬ½
    0.10
    æĸ°æĬĢæľ¯
    0.09
     behalf
    0.09
     via
    0.08
    ertools
    0.08
    åĽŀæĬ¥
    0.08
    æ·Ħ
    0.08
    ä¸Ģ个æĸ°çļĦ
    0.08
    åĽŀ头çľĭ
    0.08
    /of
    0.08
    Activations Density 0.019%

    No Known Activations