© 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. 50070
    Prev
    Next
    INDEX
    Explanations

    utility, tools, creator, manager, client, .py

    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
    ACHI
    -0.09
    æľīè¶³å¤ŁçļĦ
    -0.09
    èµĦ
    -0.08
     dol
    -0.08
    èĢ½
    -0.08
    reten
    -0.08
    llib
    -0.08
    cré
    -0.08
    ä»ĵ
    -0.08
    åħ´è¶£
    -0.08
    POSITIVE LOGITS
    å¸®ä½ł
    0.12
    çļĦ帮åĬ©
    0.11
    åı¯ä»¥å¸®åĬ©
    0.10
    æĮĩå¼ķ
    0.10
    çļĦ帮åĬ©ä¸ĭ
    0.10
    ç¨ĭåºı
    0.10
    帮å¿Ļ
    0.10
    çĩĥçħ¤
    0.10
    帮åĬ©
    0.10
    帽
    0.09
    Activations Density 0.280%

    No Known Activations