© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7222
    Prev
    Next
    INDEX
    Explanations

    minority groups and related contexts

    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
    ãģĦãģŁãģł
    -0.09
    itude
    -0.09
    ãģĦãģ£ãģŁ
    -0.08
    رÙģ
    -0.08
     Lover
    -0.08
    åħ´èµ·
    -0.08
    é²µ
    -0.08
    _LEG
    -0.08
    ä¸įåĩºæĿ¥
    -0.08
    åºķæ°Ķ
    -0.08
    POSITIVE LOGITS
    ÑĢин
    0.12
    yet
    0.10
    ouver
    0.10
    æĮ½
    0.09
    å¤ł
    0.09
    ellow
    0.09
    emachine
    0.09
    çģ¯çģ«
    0.09
    Convertible
    0.09
    .cgi
    0.09
    Activations Density 0.007%

    No Known Activations