© 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. 27739
    Prev
    Next
    INDEX
    Explanations

    wheat products and byproducts

    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
    akin
    -0.13
    ../../../
    -0.10
    ми
    -0.10
    ãĤĥ
    -0.09
    aries
    -0.08
    itarian
    -0.08
    agic
    -0.08
     nghiá»ĩm
    -0.08
    loyd
    -0.08
    çĪµ
    -0.08
    POSITIVE LOGITS
    ening
    0.13
    iness
    0.11
    ype
    0.10
    ENER
    0.10
    æ¥ŀ
    0.09
    ened
    0.09
    croft
    0.09
     Sheridan
    0.09
    ness
    0.09
    udio
    0.09
    Activations Density 0.008%

    No Known Activations