© 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. 30646
    Prev
    Next
    INDEX
    Explanations

    tea consumption or tea bags

    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
    ion
    -0.10
    ä¸įäºĨ
    -0.09
    rait
    -0.08
    ives
    -0.08
    太太
    -0.08
    cy
    -0.08
    дей
    -0.08
    ION
    -0.08
     TC
    -0.08
    ions
    -0.08
    POSITIVE LOGITS
    ников
    0.11
    èŨ
    0.10
    onomies
    0.10
    ÑĢин
    0.10
    unu
    0.10
    ë¡Ń
    0.10
    stry
    0.10
    _instructions
    0.09
     Hick
    0.09
    éĢĬ
    0.09
    Activations Density 0.008%

    No Known Activations