© 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. 56596
    Prev
    Next
    INDEX
    Explanations

    nice to VERB

    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
    å¾Īåı¯èĥ½
    -0.10
    æľĢåıĹ欢è¿İ
    -0.10
    åı¯èĥ½å¯¼èĩ´
    -0.10
    æľĢéĢĤåIJĪ
    -0.09
    ssf
    -0.09
    ä¸ĸçķĮè§Ĥ
    -0.09
    èµ°åİ»
    -0.09
    主è¦ģåĨħ容
    -0.08
    æľĢ主è¦ģ
    -0.08
    æľĢåĸľæ¬¢
    -0.08
    POSITIVE LOGITS
    çŁ¥éģĵ
    0.10
    çľĭåĪ°
    0.10
    åIJ¬åĪ°
    0.10
    _lex
    0.09
    ingers
    0.09
     rid
    0.08
    .setAction
    0.08
    éĴ¹
    0.08
    _AURA
    0.08
    ç¾İ女
    0.08
    Activations Density 0.019%

    No Known Activations