© 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. 57783
    Prev
    Next
    INDEX
    Explanations

    African-American 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
    æı´åĬ©
    -0.11
    ç»ı纪
    -0.10
     Phar
    -0.10
    好äºĭ
    -0.10
     ÑģоÑħÑĢани
    -0.10
    LER
    -0.10
    ä¾ĭè¡Į
    -0.10
    éĻĦåĬł
    -0.09
     Parties
    -0.09
    вен
    -0.09
    POSITIVE LOGITS
    1
    0.10
    0
    0.10
    3
    0.10
    2
    0.10
    5
    0.09
    7
    0.09
    4
    0.08
    8
    0.08
    9
    0.08
    è¿ģ移
    0.08
    Activations Density 0.111%

    No Known Activations