© 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. 58985
    Prev
    Next
    INDEX
    Explanations

    totally modifies adjectives

    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
     Cly
    -0.08
     Craw
    -0.08
    æ´ĭæ´ĭ
    -0.08
    steller
    -0.08
    佬
    -0.08
    Çİ
    -0.08
    åıĪ好åıĪ
    -0.08
    ä¸Ģç«Ļå¼ı
    -0.08
    强çĥĪ
    -0.08
    è¢ħ
    -0.08
    POSITIVE LOGITS
    Ñģка
    0.10
    oser
    0.10
    çķĻå®Ī
    0.10
    emarks
    0.10
    çİij
    0.09
    iors
    0.09
    ByExample
    0.09
    hots
    0.09
    okes
    0.09
    ÅĦ
    0.09
    Activations Density 0.006%

    No Known Activations