© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33636
    Prev
    Next
    INDEX
    Explanations

    as it's called

    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
    çĵ¦
    -0.10
    è¨Ģ
    -0.09
    ä¹ĥ
    -0.09
    åĮı
    -0.08
    亡
    -0.08
    RACT
    -0.08
    é©¿
    -0.08
    à¸ļà¸Ĺà¸Ħวาม
    -0.08
    ä¸Ģ件
    -0.08
     Hezbollah
    -0.08
    POSITIVE LOGITS
    人们
    0.10
    éĶĴ
    0.10
    亲åĪĩ
    0.09
    éħ£
    0.09
    éĨĴ缮
    0.09
    人åĢij
    0.09
    åĪ¥
    0.09
    éľŃ
    0.09
    åį´è¢«
    0.08
    è°IJ
    0.08
    Activations Density 0.044%

    No Known Activations