© 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. 35221
    Prev
    Next
    INDEX
    Explanations

    but, though, however

    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
    preferred
    -0.10
    èĩªçĦ¶æĺ¯
    -0.09
    å½ĵä¹ĭæĹłæĦ§
    -0.09
    æŀŃ
    -0.09
    对æĪijæĿ¥è¯´
    -0.08
    ä¸ĵ享
    -0.08
    çŀŃ
    -0.08
    æ°¸ä¸į
    -0.08
    è¯ģåĪ¸äº¤æĺĵ
    -0.08
    idd
    -0.08
    POSITIVE LOGITS
    è¿«
    0.14
    妥åįı
    0.12
    ä¸įå¾Ĺä¸į
    0.12
    çŃĶåºĶ
    0.11
    åħĭæľį
    0.11
     inev
    0.10
     compelled
    0.10
    ailer
    0.10
    强åĪ¶
    0.10
    说æľį
    0.10
    Activations Density 0.075%

    No Known Activations