© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8009
    Prev
    Next
    INDEX
    Explanations

    media genres

    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
    书ä¸Ń
    -0.10
    cloth
    -0.09
    пÑĥÑģк
    -0.08
    RCT
    -0.08
    aver
    -0.08
    rick
    -0.08
    falls
    -0.08
     Markets
    -0.08
    Stick
    -0.08
    éŀŃ
    -0.08
    POSITIVE LOGITS
    éĩĮçļĦ
    0.10
    è¯Ŀ说
    0.10
    iker
    0.10
    ishly
    0.10
    çĿĥ
    0.10
    大åħ¨
    0.09
    è¯Ŀ
    0.09
    asti
    0.09
    å¨ĥ
    0.09
    æĹ¸
    0.09
    Activations Density 0.080%

    No Known Activations