© 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. 26880
    Prev
    Next
    INDEX
    Explanations

    Nielsen ratings or Arc GIS

    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
    [email
    -0.09
     intestine
    -0.09
    æ¯ĽåŃĶ
    -0.09
    assing
    -0.09
    ç¾¹
    -0.08
    åĭĥåĭĥ
    -0.08
    ass
    -0.08
    à¸ķà¸ģ
    -0.08
    åħħçĶµ
    -0.08
     Sachs
    -0.08
    POSITIVE LOGITS
    abar
    0.10
    ä»·
    0.10
    illos
    0.09
    bulk
    0.09
    udent
    0.09
    累累
    0.09
    edList
    0.08
    人æ°Ķ
    0.08
    人家
    0.08
    imulator
    0.08
    Activations Density 0.012%

    No Known Activations