© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20723
    Prev
    Next
    INDEX
    Explanations

    "use strict" or numbers

    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
    rena
    -0.10
    verity
    -0.10
    åĵķ
    -0.09
    éĢĤ
    -0.09
    åĹĦ
    -0.09
    esy
    -0.09
    heading
    -0.08
    .digital
    -0.08
    èĢĮè¿Ļ
    -0.08
    annis
    -0.08
    POSITIVE LOGITS
    宪
    0.09
     Nä
    0.08
    ÙĴ
    0.08
     surrender
    0.08
    \AppData
    0.08
    æł·æĿ¿
    0.08
    _SS
    0.08
    amel
    0.08
    æĨ
    0.08
    opus
    0.07
    Activations Density 0.165%

    No Known Activations