© 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. 23292
    Prev
    Next
    INDEX
    Explanations

    what you can or want

    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
    akes
    -0.10
    RIX
    -0.10
    è´¯
    -0.09
    æ·Ļ
    -0.09
    ä¸Ģä½ĵ
    -0.09
    æįº
    -0.09
    ähr
    -0.09
    åı©
    -0.09
    INU
    -0.09
    æķ²
    -0.09
    POSITIVE LOGITS
     couple
    0.08
     Marr
    0.08
     virt
    0.08
    åĸĦ
    0.08
     PO
    0.08
    åĩłä¸ªäºº
    0.08
    åIJIJ
    0.08
    èµĽ
    0.08
    PO
    0.08
    å¾IJ
    0.07
    Activations Density 0.074%

    No Known Activations