© 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. 8788
    Prev
    Next
    INDEX
    Explanations

    each other

    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
    oner
    -0.09
    éļıä¹ĭ
    -0.08
    Beh
    -0.08
     Airways
    -0.08
    éĻĦ
    -0.08
    并åIJij
    -0.08
    emean
    -0.08
    quat
    -0.08
    VELO
    -0.07
    ä¸İåħ¶
    -0.07
    POSITIVE LOGITS
    们çļĦ
    0.12
    们
    0.10
    rogen
    0.10
    çĿ¦
    0.09
    éĹ´çļĦ
    0.09
    ième
    0.09
    zelf
    0.09
     sürekli
    0.08
    éħ£
    0.08
    ly
    0.08
    Activations Density 0.016%

    No Known Activations