© 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. 7729
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    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
    åŃij
    -0.10
    顼
    -0.10
    身躯
    -0.10
    ä¹Ŀ大
    -0.10
    ç»Ļå®Ŀå®Ŀ
    -0.10
    楼主
    -0.09
     recip
    -0.09
    åĩºå¤Ħ
    -0.09
    pu
    -0.09
    RIPT
    -0.09
    POSITIVE LOGITS
    wij
    0.09
     spot
    0.08
    виз
    0.08
    ä¸İåIJ¦
    0.08
    æĸĻ
    0.08
     dashes
    0.07
     Reasons
    0.07
    ÙĦغ
    0.07
     hiếm
    0.07
    (Direction
    0.07
    Activations Density 0.203%

    No Known Activations