© 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. 32643
    Prev
    Next
    INDEX
    Explanations

    places of work or commerce

    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
    å®īå±ħ
    -0.10
    æijĩ
    -0.10
    æªł
    -0.09
    æĻļæĬ¥
    -0.09
    ç¾İ人
    -0.09
    带éĺŁ
    -0.09
    é¥
    -0.09
    å¼Ģè¾Ł
    -0.08
    è¯Ľ
    -0.08
    è¿·
    -0.08
    POSITIVE LOGITS
    çĶŁäº§è½¦éĹ´
    0.15
    车éĹ´
    0.15
    å®ŀéªĮ室
    0.15
    åĬłå·¥åİĤ
    0.13
    åĮ»åĬ¡
    0.13
    å·¥åİĤ
    0.12
    å·¥ä½ľå®¤
    0.12
     studio
    0.12
     laboratory
    0.12
    åĬŀåħ¬å®¤
    0.12
    Activations Density 0.161%

    No Known Activations