© 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. 32019
    Prev
    Next
    INDEX
    Explanations

    acceptable solution/limits/level/way

    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
    ç»ĵæĻ¶
    -0.09
    好å¤Ħ
    -0.09
    å¾ĹçĽĬ
    -0.09
    aders
    -0.09
    ViewState
    -0.09
    angelo
    -0.09
    çĭIJ
    -0.09
    ìį¨
    -0.09
    Ùħت
    -0.08
    ÙĪØ´
    -0.08
    POSITIVE LOGITS
    åŃº
    0.09
    æľīä»»ä½ķ
    0.09
    æĭ¿æĿ¥
    0.09
    ãģªãģĬ
    0.08
    ä¸Ģç¯ĩ
    0.08
    å¿įåıĹ
    0.08
     fier
    0.08
     exig
    0.08
     acceptable
    0.08
     collateral
    0.08
    Activations Density 0.013%

    No Known Activations