© 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. 55804
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    ilda
    -0.09
    大éŨ
    -0.09
    æĹłçĸij
    -0.09
    odb
    -0.09
    æĶ¾å¤§
    -0.08
    åľ°å¤Ħ
    -0.08
    лов
    -0.08
    å·²äºİ
    -0.08
    race
    -0.08
    ToWorld
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģåı¥
    0.10
    å¾Ĺèµ·
    0.10
    éĹ®ä»ĸ
    0.10
    dr
    0.09
    éľĢè¦ģçĶ¨
    0.08
    æĺ¯åIJ¦æľī
    0.08
    ä¸Ģ个éĹ®é¢ĺ
    0.08
     legend
    0.08
    oba
    0.08
    ures
    0.08
    Activations Density 0.164%

    No Known Activations