© 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. 50024
    Prev
    Next
    INDEX
    Explanations

    poultry and related products

    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
    åı¯æĢľ
    -0.11
    åĸŁ
    -0.09
    .ValidationError
    -0.09
    ÑĥÑĤÑĮ
    -0.09
    å´Ĩ
    -0.09
    nes
    -0.08
    å¤ļæķ°
    -0.08
    nels
    -0.08
    amy
    -0.08
    é«ĵ
    -0.08
    POSITIVE LOGITS
    led
    0.09
    tright
    0.09
    ifer
    0.09
    craft
    0.09
    iliary
    0.09
    going
    0.08
    ment
    0.08
    nd
    0.08
    عت
    0.08
    elves
    0.08
    Activations Density 0.008%

    No Known Activations