© 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. 49735
    Prev
    Next
    INDEX
    Explanations

    better yet, better now, better known

    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
    ìn
    -0.10
    .sal
    -0.09
     Chambers
    -0.08
    âĦ
    -0.08
    èĮĤ
    -0.08
    äºĴåĬ©
    -0.08
    duk
    -0.08
    温æĥħ
    -0.08
    iego
    -0.08
    -gnu
    -0.08
    POSITIVE LOGITS
    ize
    0.11
    enton
    0.10
    izer
    0.09
     nữa
    0.09
    é«ĺæ½®
    0.09
    USH
    0.08
    anko
    0.08
    izing
    0.08
    说æĺİ
    0.08
    éªĦåĤ²
    0.08
    Activations Density 0.012%

    No Known Activations