© 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. 11373
    Prev
    Next
    INDEX
    Explanations

    starts encoding or special characters

    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
    åĪ«
    -0.10
    ĽĦ
    -0.10
    éĥ¨ä¸»ä»»
    -0.08
     briefing
    -0.08
    åĤĻ
    -0.08
    airo
    -0.08
    éĢĨ转
    -0.08
    çĽĬ
    -0.08
    è¿İ
    -0.08
    æģIJ
    -0.08
    POSITIVE LOGITS
    ä¸Ģæĸ¹éĿ¢
    0.10
     MMM
    0.09
    åĪĩæĪIJ
    0.09
    å®ŀå®ŀåľ¨åľ¨
    0.08
    çīĪæĿĥå½ĴåİŁ
    0.08
    å¨ĥ
    0.08
    æį»
    0.08
    æ·±å±Ĥ次
    0.08
     slices
    0.08
    ingly
    0.08
    Activations Density 0.084%

    No Known Activations