© 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. 30545
    Prev
    Next
    INDEX
    Explanations

    seeing or observing something

    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
    èįī
    -0.09
    说å¾Ĺ
    -0.09
    å·§
    -0.09
    è¯ħ
    -0.09
    æĥ³çĿĢ
    -0.08
    ÑĦоÑĢ
    -0.08
    è¶Ĭ大
    -0.08
    æĿ¥åĪ°äºĨ
    -0.08
    æł¹æį®èĩªå·±
    -0.08
    ovah
    -0.08
    POSITIVE LOGITS
    çļĦ表æĥħ
    0.20
    表æĥħ
    0.20
    çľ¼ç¥ŀ
    0.16
    ç¥ŀæĥħ
    0.15
    çļĦçľ¼ç¥ŀ
    0.15
    åıįåºĶ
    0.15
    çļĦç¬ij容
    0.13
    ç¬ij容
    0.13
    åıįæĩī
    0.13
    çļĦæł·åŃIJ
    0.12
    Activations Density 0.054%

    No Known Activations