© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27989
    Prev
    Next
    INDEX
    Explanations

    south-east directional phrases

    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
    çıįæĥľ
    -0.10
    å¹³æŶ
    -0.09
    /light
    -0.09
    æ¯ı次éĥ½
    -0.09
    åŁºç¡Ģ设æĸ½
    -0.09
    IDA
    -0.09
    affle
    -0.09
    ULO
    -0.09
    骨
    -0.08
    è¡¢
    -0.08
    POSITIVE LOGITS
    ç£ħ
    0.09
    æīģ
    0.09
    -flag
    0.09
    æĸ°åŁİ
    0.09
     bail
    0.08
    ään
    0.08
    isis
    0.08
    å¹ħ度
    0.08
     sick
    0.08
    潸
    0.08
    Activations Density 0.177%

    No Known Activations