© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7745
    Prev
    Next
    INDEX
    Explanations

    weight gain

    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
    çĺ¦
    -0.13
    楼ä¸Ĭ
    -0.10
    ä¸ĢæľŁ
    -0.10
    omid
    -0.10
     Ames
    -0.10
    æ·ħ
    -0.10
    ëł¹
    -0.09
    åįĸæİī
    -0.09
    榨
    -0.09
    éĶµ
    -0.09
    POSITIVE LOGITS
     век
    0.09
    è²¼
    0.09
    äºĨä¸ĢäºĽ
    0.09
    è´´
    0.09
    ç¥ŀè¯Ŀ
    0.09
    ä¸į好
    0.09
    åıįå¼¹
    0.08
    assen
    0.08
    tti
    0.08
    ipel
    0.08
    Activations Density 0.018%

    No Known Activations