© 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. 62761
    Prev
    Next
    INDEX
    Explanations

    excuse to justify

    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
     Sund
    -0.10
    esk
    -0.09
    ModelAttribute
    -0.09
    åĶ¯
    -0.09
    ail
    -0.09
    ustr
    -0.09
     Hag
    -0.08
    ICY
    -0.08
     Neville
    -0.08
     Swe
    -0.08
    POSITIVE LOGITS
    éĩıåĮĸ
    0.10
    ä¹Łå¥½
    0.10
    åľ¨å¤ĸ
    0.09
    anca
    0.09
    å½ĵå±Ģ
    0.09
    çIJ¼
    0.09
    assed
    0.08
    tero
    0.08
     Perfect
    0.08
    çĩİ
    0.08
    Activations Density 0.012%

    No Known Activations