© 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. 8669
    Prev
    Next
    INDEX
    Explanations

    beach

    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
    èī
    -0.09
    ELY
    -0.09
    ley
    -0.09
    è·Łä½ł
    -0.08
    ip
    -0.08
    LOT
    -0.08
    å°ĸ
    -0.08
    éģĹæ¼ı
    -0.08
    æĶ¹æŃ£
    -0.08
    æĿIJ
    -0.08
    POSITIVE LOGITS
    è¯Ŀ说
    0.10
    -lined
    0.10
    ashes
    0.09
    _HAL
    0.09
    æ¦ľ
    0.09
    vat
    0.09
     Pública
    0.08
    Opens
    0.08
    纵
    0.08
    -olds
    0.08
    Activations Density 0.006%

    No Known Activations