© 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. 54834
    Prev
    Next
    INDEX
    Explanations

    received treatment

    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
    bras
    -0.10
    ylon
    -0.10
    åĪĩ
    -0.10
     returnUrl
    -0.10
    ãģĸ
    -0.09
    enthal
    -0.09
    ç»ĻåĩºäºĨ
    -0.09
     Pee
    -0.09
    çĶ»éĿ¢
    -0.09
    仪
    -0.09
    POSITIVE LOGITS
    åºĶæľīçļĦ
    0.12
    å®ŀæĥł
    0.11
    好å¤Ħ
    0.10
    æĪĸå¤ļæĪĸå°ij
    0.10
    åģĩåĨĴ
    0.09
    å¾ħéģĩ
    0.09
    åīįæīĢ
    0.09
    ä¸İåħ¶
    0.08
    ä¸İä¼Ĺ
    0.08
    饼
    0.08
    Activations Density 0.076%

    No Known Activations