© 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. 34696
    Prev
    Next
    INDEX
    Explanations

    white Americans

    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
    åŁºæķ°
    -0.10
    讯
    -0.09
    anted
    -0.09
    èģ
    -0.09
     Ùħض
    -0.09
    sink
    -0.09
     ÑģобиÑĢа
    -0.08
    ড
    -0.08
    _VOID
    -0.08
    meta
    -0.08
    POSITIVE LOGITS
    èĤ¤
    0.09
    dur
    0.08
    é¡·
    0.08
     Lil
    0.08
    py
    0.08
    ÑĨеп
    0.08
    ä¹IJæĦı
    0.07
     Siber
    0.07
    çľī
    0.07
    çŃ¾
    0.07
    Activations Density 0.014%

    No Known Activations