© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52355
    Prev
    Next
    INDEX
    Explanations

    coating or covered with material

    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
    以åħį
    -0.10
    æľĢå¿«
    -0.09
     tslib
    -0.09
     Estates
    -0.09
    ÑĤика
    -0.09
    åħ³éŨ
    -0.08
    éĿ
    -0.08
     ÙĦÙĩذا
    -0.08
     Smy
    -0.08
    ä¾ĭå¤ĸ
    -0.08
    POSITIVE LOGITS
    antes
    0.10
    udas
    0.09
    ante
    0.09
    beit
    0.08
    ANTE
    0.08
    shake
    0.08
    èŁł
    0.08
     shaking
    0.08
    Ñģен
    0.08
    éĿĻéĿĻåľ°
    0.08
    Activations Density 0.002%

    No Known Activations