© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36698
    Prev
    Next
    INDEX
    Explanations

    Cochrane Central Register

    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
    注
    -0.09
     sa
    -0.09
    èĦIJ
    -0.08
    建ç«ĭèµ·
    -0.08
    æ¾İ
    -0.08
    WX
    -0.08
    åĢ¬
    -0.08
     kn
    -0.08
    isky
    -0.08
    å¹²éĥ¨
    -0.08
    POSITIVE LOGITS
    /meta
    0.12
    (meta
    0.12
     meta
    0.12
    åIJĦåĽ½
    0.10
    itta
    0.10
    æ°¸æģĴ
    0.10
    -meta
    0.10
    Meta
    0.09
    META
    0.09
    èĶ½
    0.09
    Activations Density 0.504%

    No Known Activations