© 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. 11211
    Prev
    Next
    INDEX
    Explanations

    bottle and related items

    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
    åľ°ä¸Ńæµ·
    -0.11
    ness
    -0.10
    es
    -0.10
    mit
    -0.09
    esse
    -0.09
    èĹķ
    -0.09
    人士
    -0.09
    onis
    -0.09
    shire
    -0.09
    å¸ĸåŃIJ
    -0.09
    POSITIVE LOGITS
    ting
    0.11
    anguage
    0.10
    DAQ
    0.09
    swana
    0.09
    ptic
    0.09
    inja
    0.09
    åĿļåĽº
    0.08
    воÑĢ
    0.08
    ä¸Ģä¸Ŀ
    0.08
    ãģĬãģı
    0.08
    Activations Density 0.008%

    No Known Activations