© 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. 23439
    Prev
    Next
    INDEX
    Explanations

    si followed by specific words

    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
    姥
    -0.10
    å·´å·´
    -0.10
    åĬłçĽĸ
    -0.09
    rea
    -0.09
    usercontent
    -0.08
    éĽ¾
    -0.08
    ynes
    -0.08
    éĴµ
    -0.08
    furt
    -0.08
    骺
    -0.08
    POSITIVE LOGITS
    ities
    0.10
    èĤļ
    0.10
    uate
    0.09
    aty
    0.09
    个å¤ļ
    0.09
    æĺ¯è¦ģ
    0.09
    åģļä¸įåĪ°
    0.09
    æĹ¥åŃIJ
    0.09
    ons
    0.09
    è§Ħ模æľĢ大
    0.08
    Activations Density 0.056%

    No Known Activations