© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20203
    Prev
    Next
    INDEX
    Explanations

    side navigation or panel

    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
    ivor
    -0.11
    ras
    -0.09
    æīĢåľ¨åľ°
    -0.09
    iten
    -0.09
     Southern
    -0.09
    æīĢåľ¨
    -0.08
    achel
    -0.08
    WXYZ
    -0.08
    æīĢåľ¨çļĦ
    -0.08
    airo
    -0.08
    POSITIVE LOGITS
    åIJ¾
    0.10
    ä¸ĭåįĬ
    0.09
    左侧
    0.09
    ç¦
    0.09
     vig
    0.09
    两侧
    0.08
    afia
    0.08
    èľĥ
    0.08
    å¹ħ
    0.08
    åĬŁå¤«
    0.08
    Activations Density 0.041%

    No Known Activations