© 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. 4184
    Prev
    Next
    INDEX
    Explanations

    real-life contexts

    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
    è²Į
    -0.10
    è¢į
    -0.09
    rück
    -0.09
    é¸
    -0.08
    å¤©çľŁ
    -0.08
    çĭİ
    -0.08
     naw
    -0.08
    ograd
    -0.08
    ehr
    -0.08
    åŃĽ
    -0.08
    POSITIVE LOGITS
    顺
    0.09
    æĭħå½ĵ
    0.09
     expectancy
    0.09
    å¨ģåĬĽ
    0.09
    çīµæīĭ
    0.08
    åĽ½æĥħ
    0.08
    éłĨ
    0.08
    ÐŀÐł
    0.08
    -Sep
    0.08
    å©ļ姻
    0.08
    Activations Density 0.006%

    No Known Activations