© 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. 10822
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    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
    _addresses
    -0.10
    çĹħåıĺ
    -0.09
    agner
    -0.09
    è£ģ
    -0.09
    china
    -0.08
    ennes
    -0.08
    æļ®
    -0.08
    æĸ°ä¸ĸ纪
    -0.08
    ogl
    -0.08
    è¿ĻåĿĹ
    -0.08
    POSITIVE LOGITS
    称ä¹ĭ为
    0.11
    æĭ¿èµ·
    0.09
    åĨįåĬłä¸Ĭ
    0.09
    导åIJij
    0.08
    æĽ´åIJį为
    0.08
     militar
    0.08
    å¿ĺ
    0.08
    iben
    0.08
    äs
    0.08
    elled
    0.08
    Activations Density 0.069%

    No Known Activations