© 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. 4641
    Prev
    Next
    INDEX
    Explanations

    type of

    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
    dio
    -0.09
     lẽ
    -0.08
    ude
    -0.08
    nier
    -0.08
    ย
    -0.08
    éĩįéĩį
    -0.08
    太åIJİ
    -0.08
    åİļåİļ
    -0.08
    Ùĥار
    -0.08
    antha
    -0.08
    POSITIVE LOGITS
    ë³Ħ
    0.10
    ä¸įä¹ı
    0.10
     dáng
    0.09
    casting
    0.09
    ahead
    0.09
    ake
    0.09
    ï¸ı
    0.09
    çļĦç²¾ç¥ŀ
    0.09
    aths
    0.09
    иÑĩно
    0.09
    Activations Density 0.103%

    No Known Activations