© 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. 19629
    Prev
    Next
    INDEX
    Explanations

    sentence terminators

    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
    çŃīçŃī
    -0.10
    rites
    -0.10
    æĪĸèĢħæĺ¯
    -0.10
    ITED
    -0.09
    èħ¥
    -0.09
    .mx
    -0.09
    å¤Ħå¤Ħ
    -0.09
    èĻij
    -0.09
    æĥ³æ³ķ
    -0.09
    åŃĺåľ¨çĿĢ
    -0.08
    POSITIVE LOGITS
    æŶéĹ´åĴĮ
    0.09
    Aware
    0.09
     коÑĤоÑĢ
    0.09
    Ä±ÅŁÄ±
    0.08
    åľ¨åŃ¦æł¡
    0.08
    ä¼ģä¸ļåĴĮ
    0.08
    å®Ĺ
    0.08
    æĹłäºº
    0.08
    ãģ§ãģĻãģĮ
    0.08
    æľīæľŁ
    0.08
    Activations Density 0.436%

    No Known Activations