© 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. 10235
    Prev
    Next
    INDEX
    Explanations

    service termination

    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
    rets
    -0.08
    æŀ¥
    -0.08
    elts
    -0.08
    æĿŀ
    -0.08
    æĭĽ
    -0.08
    åģľè½¦åľº
    -0.08
    è¿ĪåIJij
    -0.08
     наÑĢ
    -0.08
    rit
    -0.08
    æŃª
    -0.08
    POSITIVE LOGITS
    onio
    0.10
    çĽ´è¾¾
    0.09
    å¤ĩ
    0.09
    æ»ĩ
    0.09
    åħ¨ç¨ĭ
    0.09
     Mig
    0.09
     tre
    0.09
    çĽĪ
    0.09
    å°Ĭ
    0.09
    è§ī
    0.09
    Activations Density 0.055%

    No Known Activations