© 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. 57294
    Prev
    Next
    INDEX
    Explanations

    many people

    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
    主è¦ģæľī
    -0.11
    ä»»ä½ķ人
    -0.10
     mostly
    -0.10
    æŁIJäºĽ
    -0.10
     sometimes
    -0.10
     иногда
    -0.10
    æľīä»»ä½ķ
    -0.09
    æīĢæľī人éĥ½
    -0.09
     everyone
    -0.09
    ä¸Ģå¾ĭ
    -0.09
    POSITIVE LOGITS
    çĶļèĩ³æĺ¯
    0.13
    æı©
    0.10
    éĤ¦
    0.10
    /all
    0.10
    å°¤åħ¶æĺ¯
    0.10
    ä¸įåIJĮç¨ĭ度
    0.10
    çĶ¬
    0.10
    -many
    0.09
    uem
    0.09
    çĶŁäº§çĶŁæ´»
    0.09
    Activations Density 0.163%

    No Known Activations