© 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. 30663
    Prev
    Next
    INDEX
    Explanations

    regular, consistently, each

    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
    OSP
    -0.12
    åĬłåĢį
    -0.11
    ç¢Ľ
    -0.10
    æıIJåīį
    -0.10
    лик
    -0.09
    wer
    -0.09
    ADR
    -0.09
    é¢Ĩ
    -0.09
    ITT
    -0.09
     Lá»ĭch
    -0.09
    POSITIVE LOGITS
    ç»ı常
    0.12
     xuyên
    0.12
    æŶåĪ»
    0.10
    ç¶ĵ常
    0.10
    é¢ijçİĩ
    0.10
    ä¸įæĸŃåľ°
    0.09
    å®ļæľŁ
    0.09
     regularly
    0.09
    æĺ¯æĪijåĽ½
    0.09
    ç»ı常ä¼ļ
    0.09
    Activations Density 0.077%

    No Known Activations