© 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. 1629
    Prev
    Next
    INDEX
    Explanations

    leather jacket, purse, bar

    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
    egis
    -0.10
    æĺ¥å¤©
    -0.10
     UPC
    -0.10
    èīĩ
    -0.10
    åįĪé¤IJ
    -0.10
    _keywords
    -0.10
    ete
    -0.10
    çļĦåį°è±¡
    -0.10
    æĦīæĤ¦
    -0.09
    èĪ´
    -0.09
    POSITIVE LOGITS
     som
    0.09
     Pearce
    0.08
    èįĨ
    0.08
    为空
    0.08
    çįIJ
    0.08
    som
    0.08
    راÙĩ
    0.08
    биÑĤ
    0.08
    ::$_
    0.08
    éĹ·
    0.08
    Activations Density 0.073%

    No Known Activations