© 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. 20237
    Prev
    Next
    INDEX
    Explanations

    others and more

    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
     оÑĢганизм
    -0.10
    bih
    -0.09
     herr
    -0.09
    ç©
    -0.09
    iew
    -0.09
    гаÑĢ
    -0.08
    è¿Ļ两ç§į
    -0.08
    ило
    -0.08
    è¦ģæ¯Ķ
    -0.08
    loo
    -0.08
    POSITIVE LOGITS
     others
    0.36
    others
    0.29
     Others
    0.27
    Others
    0.26
    ä»ĸ人
    0.24
    åħ¶ä»ĸ人
    0.22
    åĪ«äºº
    0.21
    åĪ«äººçļĦ
    0.17
     ones
    0.17
    åĪ¥äºº
    0.17
    Activations Density 0.127%

    No Known Activations