© 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. 56696
    Prev
    Next
    INDEX
    Explanations

    polo and preppy outfits

    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
    ä¸ĢæĹ¥
    -0.09
    çĥ
    -0.09
    hips
    -0.08
    èµĦæĸĻæĺ¾ç¤º
    -0.08
    ileen
    -0.08
    ritable
    -0.08
    melon
    -0.08
    éĶ£
    -0.08
    Parcelable
    -0.08
     Pert
    -0.08
    POSITIVE LOGITS
     stakes
    0.09
    åı¯ä»¥ä»İ
    0.09
    inth
    0.09
    渥
    0.09
    ä»ĸä¹Ł
    0.08
    olla
    0.08
    æįĤ
    0.08
    egin
    0.08
    ocks
    0.08
    ads
    0.08
    Activations Density 0.001%

    No Known Activations