© 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. 23907
    Prev
    Next
    INDEX
    Explanations

    thanking and congratulating

    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
    ä»»ä½ķ人éĥ½
    -0.09
    人çī©
    -0.09
    è¶Ĭ
    -0.09
    å·²ä¹ħ
    -0.08
    è¿ĺæľīå¾Īå¤ļ
    -0.08
    çıŀ
    -0.08
    ç¦ģåĮº
    -0.08
     Minds
    -0.08
    èĭĽ
    -0.08
    ECT
    -0.08
    POSITIVE LOGITS
    ä¹ĭä½Ļ
    0.11
    èݽ
    0.09
    Thunk
    0.09
    并对
    0.09
     Pru
    0.09
    并ä¸İ
    0.09
    éĵ
    0.09
    ä¼ļä¸Ĭ
    0.08
    ä¸Ģçķª
    0.08
    èIJ½ä¸ĭ
    0.08
    Activations Density 0.164%

    No Known Activations