© 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. 31536
    Prev
    Next
    INDEX
    Explanations

    unit count

    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
    antha
    -0.10
    çģ«éĶħ
    -0.09
    æ´ĭæ´ĭ
    -0.08
    indow
    -0.08
    åij½
    -0.08
    vara
    -0.08
    isen
    -0.08
    fp
    -0.08
    peq
    -0.07
    天天
    -0.07
    POSITIVE LOGITS
    æķ°éĩı
    0.12
    鹤
    0.10
     اÙĦÙĪاØŃد
    0.10
    ãĥĥãĥĦ
    0.10
    æĮ¨
    0.10
    çļĦæķ°éĩı
    0.09
    åĬ³åĬ¨åĬĽ
    0.09
    .toObject
    0.09
    _quantity
    0.09
    é¹³
    0.09
    Activations Density 0.038%

    No Known Activations