© 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. 31375
    Prev
    Next
    INDEX
    Explanations

    cultural validity and value

    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
    auce
    -0.11
     ldc
    -0.10
    VILLE
    -0.10
    /check
    -0.09
    cies
    -0.09
    è¸ŀ
    -0.09
    空æ°ĶåĩĢåĮĸ
    -0.09
    hood
    -0.09
    æĥĬ人
    -0.09
    enson
    -0.09
    POSITIVE LOGITS
    ifact
    0.10
    ä¹łä¿Ĺ
    0.09
    ç¥Ĺ
    0.09
    ستاÙĨ
    0.09
    UNKNOWN
    0.09
    IRM
    0.09
    ừng
    0.08
    æ½
    0.08
    etheless
    0.08
    ually
    0.08
    Activations Density 0.015%

    No Known Activations