© 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. 38485
    Prev
    Next
    INDEX
    Explanations

    cause or reason questions

    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
    eted
    -0.10
    彦
    -0.10
     اÙĦÙħستÙĤبÙĦ
    -0.09
    å±ķæľĽ
    -0.09
    å°Ĩ继ç»Ń
    -0.09
    å·²ç»ıè¶ħè¿ĩ
    -0.09
    åıªä¸įè¿ĩæĺ¯
    -0.09
    帮åĬ©ä¼ģä¸ļ
    -0.09
    åı«æĪij
    -0.09
    çł´
    -0.09
    POSITIVE LOGITS
    åı¯èĥ½æĢ§
    0.16
    çļĦåı¯èĥ½æĢ§
    0.15
    ä¸įåı¯èĥ½
    0.15
    ä¹Łä¸įåı¯èĥ½
    0.12
     possibilities
    0.12
    æĢİä¹Īåı¯èĥ½
    0.12
    å¾Īæľīåı¯èĥ½
    0.12
    å¾Īåı¯èĥ½
    0.12
    æĺ¯ä¸įåı¯èĥ½
    0.12
    æľīåı¯èĥ½
    0.11
    Activations Density 0.141%

    No Known Activations