© 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. 51470
    Prev
    Next
    INDEX
    Explanations

    slapped

    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
    urance
    -0.10
    æĽ²æĬĺ
    -0.10
    å°ıå°ı
    -0.09
    ãģ³
    -0.09
    Pts
    -0.09
    éĤ¹
    -0.09
     sled
    -0.08
    æľīä¸ĢçĤ¹
    -0.08
     slightest
    -0.08
    æħ¢æħ¢
    -0.08
    POSITIVE LOGITS
    itude
    0.10
    леп
    0.09
    ichten
    0.09
    çī¢
    0.09
     onto
    0.09
    åľ¨ä¸Ģèµ·
    0.09
    æīĵåĵį
    0.09
    ToDevice
    0.08
    ç¨Ģ
    0.08
    onto
    0.08
    Activations Density 0.017%

    No Known Activations