© 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. 21710
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ız
    -0.10
    sip
    -0.09
    hiba
    -0.09
    agger
    -0.09
    hai
    -0.09
    æ¯Ĵ
    -0.09
     deceptive
    -0.08
    еÑĨ
    -0.08
    箧
    -0.08
    åģļåĪ°äºĨ
    -0.08
    POSITIVE LOGITS
    ened
    0.13
     heights
    0.10
    ening
    0.10
    é«ĺ度
    0.10
     Heights
    0.10
    æĪĸå¤ļ
    0.10
    çļĦé«ĺ度
    0.10
    以ä¸ĭæĺ¯
    0.09
    ä¸ĢåŃĹ
    0.09
    uate
    0.09
    Activations Density 0.006%

    No Known Activations