© 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. 48146
    Prev
    Next
    INDEX
    Explanations

    cancel or cancellation

    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
    olib
    -0.10
    河水
    -0.10
    å¹Ħ
    -0.09
    æ¥
    -0.09
    çģ«çĥ§
    -0.09
    querque
    -0.09
    å³Ļ
    -0.09
    å°Ĭæķ¬
    -0.09
    鼷æĸ¯
    -0.09
     Brewing
    -0.08
    POSITIVE LOGITS
     previous
    0.10
    enha
    0.09
     hẳn
    0.09
    宵
    0.09
    åİŁæľīçļĦ
    0.09
    ä¸Ģ页
    0.09
    æİī
    0.08
     plans
    0.08
    æīĭä¸ŃçļĦ
    0.08
    ä¸Ģ个个
    0.08
    Activations Density 0.050%

    No Known Activations