© 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. 51546
    Prev
    Next
    INDEX
    Explanations

    take part in

    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
    _echo
    -0.10
    enso
    -0.09
    被æĬĵ
    -0.09
    ally
    -0.09
    éĽªå±±
    -0.09
    ritz
    -0.08
    æĿŁ
    -0.08
    é¢Ĩ
    -0.08
    çļ¿
    -0.08
    æŀ·
    -0.08
    POSITIVE LOGITS
    æİĩ
    0.11
    èĵĦ
    0.09
    aise
    0.09
    actoring
    0.09
    ASA
    0.09
    æĽĻ
    0.08
    éĹ®éĹ®
    0.08
    à¹Ģà¸ĭ
    0.08
    .gms
    0.08
    ä¼¼
    0.08
    Activations Density 0.004%

    No Known Activations