© 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. 52177
    Prev
    Next
    INDEX
    Explanations

    reporting

    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
    çĥ¦æģ¼
    -0.09
    èĭ«
    -0.09
    elige
    -0.08
    æ°¸ä¹ħ
    -0.08
    åĿ
    -0.08
    .Ribbon
    -0.08
    æł¼å°Ķ
    -0.08
    Fallback
    -0.08
     rule
    -0.08
     permanent
    -0.08
    POSITIVE LOGITS
    edly
    0.11
    /report
    0.11
    æĬ¥åijĬ
    0.11
    (report
    0.11
    å·¥ä½ľæĬ¥åijĬ
    0.11
     reports
    0.11
    report
    0.10
    reports
    0.10
     report
    0.10
    REPORT
    0.10
    Activations Density 0.129%

    No Known Activations