© 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. 49434
    Prev
    Next
    INDEX
    Explanations

    wordpress websites and domains

    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
    èĪŁ
    -0.10
    çĶ¸
    -0.10
    DOM
    -0.09
    çĬĢ
    -0.09
    岿
    -0.09
    åħ¨åľº
    -0.08
    å´ĩé«ĺ
    -0.08
    å¾ĹäºĨ
    -0.08
    çĻ¾å¼º
    -0.08
    .pagination
    -0.08
    POSITIVE LOGITS
    reas
    0.09
    åĨľä¸ļåĨľæĿij
    0.09
    æħİéĩį
    0.08
    avic
    0.08
    ason
    0.08
    æĿ
    0.08
     Malik
    0.08
    èĦ±ç¦»
    0.08
    åIJĦä½į
    0.08
    æĭIJ
    0.08
    Activations Density 0.002%

    No Known Activations