© 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. 7875
    Prev
    Next
    INDEX
    Explanations

    total or altogether

    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
    YTE
    -0.10
    尤为éĩįè¦ģ
    -0.09
    毫
    -0.09
    /MPL
    -0.09
    è¡®
    -0.09
    å¾Ĺèµ·
    -0.09
    bron
    -0.09
     perd
    -0.09
     Mess
    -0.09
    æ²»çĹħ
    -0.08
    POSITIVE LOGITS
    åħ±æľī
    0.11
    овал
    0.09
    éĢł
    0.09
    èĥĮéĥ¨
    0.09
    室å¤ĸ
    0.09
    ãĤ
    0.09
    èĢ³
    0.09
    azi
    0.09
    asia
    0.08
    è£ģ
    0.08
    Activations Density 0.028%

    No Known Activations