© 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. 49262
    Prev
    Next
    INDEX
    Explanations

    feeling confident or uneasy

    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
    å¾ħéģĩ
    -0.10
    棺
    -0.10
    ä½ĵè´´
    -0.10
    å¦Ĵ
    -0.10
    éªŀ
    -0.10
    abay
    -0.09
    èĢĮæĿ¥
    -0.09
    误ä¼ļ
    -0.09
    ä¸įæľį
    -0.09
    寤
    -0.09
    POSITIVE LOGITS
    æĭ¾
    0.08
    hos
    0.08
    ollow
    0.08
    Lat
    0.08
    çľĭæ¸ħ
    0.08
    说èĩªå·±
    0.07
    ance
    0.07
     spons
    0.07
    积åĪĨ
    0.07
     Kore
    0.07
    Activations Density 0.048%

    No Known Activations