© 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. 18336
    Prev
    Next
    INDEX
    Explanations

    eukaryotic, eureka

    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
    piece
    -0.09
    éªij
    -0.09
     ØŃسÙĬÙĨ
    -0.09
    éĺ´å½±
    -0.09
    UCH
    -0.09
    .od
    -0.09
    åĸ
    -0.08
    erva
    -0.08
    à¹Ħหว
    -0.08
    friends
    -0.08
    POSITIVE LOGITS
    cors
    0.10
    çªĪ
    0.09
    åµĺ
    0.09
    ä¸įæĺİçĻ½
    0.09
    éŨåı£
    0.09
    zer
    0.09
    ä¹Łæľīä¸ĢäºĽ
    0.09
    GLOBALS
    0.09
    aurant
    0.08
    ingly
    0.08
    Activations Density 0.004%

    No Known Activations