© 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. 55434
    Prev
    Next
    INDEX
    Explanations

    self-made or custom-built

    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
     cle
    -0.09
    åļİ
    -0.09
    人éĹ´
    -0.09
    çŃ
    -0.08
     Grace
    -0.08
    æĤ¨çļĦ
    -0.08
    æĭĽåij¼
    -0.08
    SHIP
    -0.08
    çĵ·çłĸ
    -0.08
    æĹłå¿§
    -0.08
    POSITIVE LOGITS
    èĩªåĪ¶
    0.28
     homemade
    0.22
    èĩªè¡Į
    0.19
     custom
    0.17
     Homemade
    0.17
    èĩªä¸»çłĶåıij
    0.16
    å®ļåĪ¶
    0.16
    åĪ¶ä½ľ
    0.15
    custom
    0.15
     DIY
    0.15
    Activations Density 0.190%

    No Known Activations