© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19478
    Prev
    Next
    INDEX
    Explanations

    succulent, plant, ears

    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
    worth
    -0.10
    ly
    -0.09
    grounds
    -0.09
    èİ·åĪ©
    -0.09
    lasting
    -0.09
    ight
    -0.09
    ment
    -0.09
    uden
    -0.09
    æµħ
    -0.09
    ä¸Ģ大åłĨ
    -0.09
    POSITIVE LOGITS
    okit
    0.10
    主ä¹īèĢħ
    0.09
    æ£ļ
    0.09
    кÑĢи
    0.09
    ä¾ł
    0.09
    身亡
    0.09
    ylon
    0.09
    éŀ£
    0.08
    买家
    0.08
    /umd
    0.08
    Activations Density 0.007%

    No Known Activations