© 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. 34611
    Prev
    Next
    INDEX
    Explanations

    peptide, peptides, ptide, peptoid

    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
    ses
    -0.12
    ories
    -0.10
    пеÑĩаÑĤ
    -0.10
    ioni
    -0.09
    è¹ĭ
    -0.09
    sen
    -0.09
     lẽ
    -0.09
    人群ä¸Ń
    -0.09
    ional
    -0.08
    aret
    -0.08
    POSITIVE LOGITS
    ../../../
    0.11
    å¾Ĺèµ·
    0.10
    doll
    0.10
    formance
    0.10
    isson
    0.09
    pler
    0.09
    stakes
    0.09
    oples
    0.09
    acock
    0.09
    inding
    0.09
    Activations Density 0.071%

    No Known Activations