© 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. 3615
    Prev
    Next
    INDEX
    Explanations

    let me know

    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
    åľ°å¤Ħ
    -0.09
    CEE
    -0.09
    dre
    -0.09
    å¦Ĥæŀľä¸įæĺ¯
    -0.09
    称ä¹ĭ为
    -0.09
    ä½łçŁ¥éģĵ
    -0.09
     freder
    -0.09
    íıIJ
    -0.09
    OrNull
    -0.08
    _Normal
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.10
    èįĥ
    0.09
     indeed
    0.09
    ä¸Ĭæ¼Ķ
    0.08
    çıł
    0.08
    éĹ´çļĦ
    0.08
    ä»Ģä¹ĪæŶåĢĻ
    0.08
    å¹
    0.08
    -parent
    0.08
    åIJĪçIJĨæĢ§
    0.08
    Activations Density 0.015%

    No Known Activations