© 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. 33613
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency and need

    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
    çĮ·
    -0.10
    æ´Ĺ澡
    -0.09
    åIJĮæł·çļĦ
    -0.09
    åľ¨æİ¥åıĹ
    -0.09
    nap
    -0.09
    æĸ°ä¸Ģ代
    -0.09
    æĪij们åı¯ä»¥
    -0.09
    禹
    -0.08
    椿
    -0.08
    ä¸įä»ħåı¯ä»¥
    -0.08
    POSITIVE LOGITS
    é¢ijç¹ģ
    0.17
    çļĦéľĢæ±Ĥ
    0.13
    éľĢæ±Ĥ
    0.12
    éľĢè¦ģ
    0.12
     needs
    0.12
    è¿«åĪĩ
    0.11
    éľĢè¦ģçĶ¨åĪ°
    0.11
    ç»ı常
    0.11
    è¿ĺæĥ³
    0.11
     needing
    0.11
    Activations Density 0.539%

    No Known Activations