© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21113
    Prev
    Next
    INDEX
    Explanations

    for accuracy

    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
    è£ķ
    -0.10
    lj
    -0.09
    èĢĢ
    -0.08
    èij«
    -0.08
     DRIVE
    -0.08
    hol
    -0.08
    磾
    -0.08
    çļĦçģµéŃĤ
    -0.08
    åı·çłģ
    -0.08
     tint
    -0.08
    POSITIVE LOGITS
    STYPE
    0.09
    交éĶĻ
    0.09
    梦è§ģ
    0.09
    äºĨä¸Ģ份
    0.08
    æIJŀ
    0.08
    ardon
    0.08
    uant
    0.08
    åįģ足
    0.08
    衾
    0.08
    漪
    0.08
    Activations Density 0.015%

    No Known Activations