© 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. 55171
    Prev
    Next
    INDEX
    Explanations

    words ending in ility or ivity

    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
    éĢŀ
    -0.10
     panda
    -0.09
    ç»ĦæĪIJçļĦ
    -0.09
    (s
    -0.09
    èĬ±æł·
    -0.09
    çļĦåŃĺåľ¨
    -0.08
    们çļĦ
    -0.08
    çĹķ迹
    -0.08
    sWith
    -0.08
    太å°ij
    -0.08
    POSITIVE LOGITS
    æĸ¹éĿ¢çļĦ
    0.17
    æĸ¹éĿ¢
    0.13
     issues
    0.12
    ä¸į好
    0.11
    ä¸įä½³
    0.11
    -threatening
    0.10
    éĹ®é¢ĺ
    0.10
    acyj
    0.10
    è¿Ļ个éĹ®é¢ĺ
    0.10
    æĢ§
    0.10
    Activations Density 0.548%

    No Known Activations