© 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. 62800
    Prev
    Next
    INDEX
    Explanations

    golf

    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
    aml
    -0.10
    hood
    -0.10
    OfWork
    -0.10
    éĻIJãĤĬ
    -0.09
    好äºĭ
    -0.09
    alist
    -0.09
    åŃĹåı·
    -0.09
    gli
    -0.09
    alink
    -0.08
     rÃłng
    -0.08
    POSITIVE LOGITS
    smith
    0.14
    ered
    0.10
    bras
    0.10
    æ¤ħ
    0.10
    ers
    0.10
    ìį¨
    0.10
    etty
    0.09
    ongan
    0.09
    ing
    0.09
    éĨļ
    0.09
    Activations Density 0.007%

    No Known Activations