© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50476
    Prev
    Next
    INDEX
    Explanations

    image artifacts

    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
     unfold
    -0.10
    unfold
    -0.09
     Zwe
    -0.09
    é¢ĸ
    -0.09
    åįĹæ²Ļ
    -0.09
     Twe
    -0.09
    ingo
    -0.09
    åļ
    -0.09
    acic
    -0.08
    å¤ĸåĮħ
    -0.08
    POSITIVE LOGITS
    å¹²æī°
    0.12
    çݰ象
    0.12
     artifacts
    0.11
    artifact
    0.10
    è´¨éĩıéĹ®é¢ĺ
    0.10
    æķĪæŀľ
    0.10
    æĮİ
    0.10
     unwanted
    0.10
    çŃīéĹ®é¢ĺ
    0.10
     artifact
    0.10
    Activations Density 0.201%

    No Known Activations