© 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. 56186
    Prev
    Next
    INDEX
    Explanations

    queen, bees, mother

    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
    鹿
    -0.10
     lur
    -0.09
    æĭĺ
    -0.09
    ël
    -0.08
    èĻİ
    -0.08
    å®¡æł¸
    -0.08
     lil
    -0.08
    鸡
    -0.08
    /root
    -0.08
    imedia
    -0.08
    POSITIVE LOGITS
    æ»Ł
    0.11
    å¿ĻçĿĢ
    0.11
    é«ĵ
    0.10
    åĵģç±»
    0.10
    æĥ³ä¸įåĪ°
    0.10
    ç³Ĭæ¶Ĥ
    0.09
    æĭĻ
    0.09
    å´¤
    0.09
    ç¥ĩ
    0.09
    佩æľį
    0.09
    Activations Density 0.061%

    No Known Activations