© 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. 23316
    Prev
    Next
    INDEX
    Explanations

    methylation and transfer

    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
    ĸī
    -0.08
    æ¹į
    -0.08
    æĶ¹æŃ£
    -0.08
     squ
    -0.08
    ÑģÑĥд
    -0.08
    åĸī
    -0.08
    rium
    -0.08
    çļĦå®ŀåĬĽ
    -0.08
    elves
    -0.08
    æľ¬äºĭ
    -0.08
    POSITIVE LOGITS
    len
    0.09
    scene
    0.09
    ç¾½æ¯Ľ
    0.09
    Trail
    0.09
    åĩ»
    0.09
    çĶŁæĢģä¿ĿæĬ¤
    0.09
    åħ¥åħļ
    0.08
    æľ´ç´ł
    0.08
    .decorate
    0.08
     McConnell
    0.08
    Activations Density 0.500%

    No Known Activations