© 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. 39281
    Prev
    Next
    INDEX
    Explanations

    ornament, ornate, ornithine, Ornstein

    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
     dozen
    -0.10
    rown
    -0.10
    念头
    -0.09
    ðŁı»
    -0.09
    boards
    -0.09
    ľ
    -0.09
    TURE
    -0.09
    боÑĢ
    -0.09
    ¶
    -0.08
    -0.08
    POSITIVE LOGITS
    ifacts
    0.11
    çŀŃ
    0.10
    als
    0.10
    phans
    0.10
    ments
    0.10
    ANGE
    0.10
    thew
    0.10
    alist
    0.10
    shire
    0.10
    chaft
    0.10
    Activations Density 0.004%

    No Known Activations