© 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. 17833
    Prev
    Next
    INDEX
    Explanations

    significant caregivers and social relationships

    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
    /fr
    -0.10
    天æīį
    -0.10
    éķ¯
    -0.10
    ниÑĩ
    -0.09
    اش
    -0.09
    çĬ¶åħĥ
    -0.09
     ÑģебÑı
    -0.09
    ä¸įåĥı
    -0.09
    itaire
    -0.09
    ä¸İæŶ
    -0.09
    POSITIVE LOGITS
    æĬļåħ»
    0.10
    akis
    0.09
    æĭ¯
    0.09
    åľ¨ä¹İ
    0.08
    è´¢ç¨İ
    0.08
    Vir
    0.08
    代çIJĨ人
    0.08
    ESIS
    0.08
    æİ¥åĬĽ
    0.08
     Tob
    0.08
    Activations Density 0.046%

    No Known Activations