© 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. 32214
    Prev
    Next
    INDEX
    Explanations

    host of / slew of

    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
    ä¸Ģåı¥è¯Ŀ
    -0.09
     Ches
    -0.09
    涵
    -0.09
    avid
    -0.09
    ä¸Ģæŀļ
    -0.09
    owers
    -0.08
    æĹ¥æĬ¥ç¤¾
    -0.08
    سÙĬر
    -0.08
    æĮºå¥½
    -0.08
    æŁIJäºĽ
    -0.08
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.13
    åħ¶ä»ĸ人
    0.11
    åIJĦæł·
    0.10
     other
    0.10
    åħ¶ä»ĸ
    0.10
    oting
    0.10
    åħ¶å®ĥ
    0.10
    ocop
    0.10
    大大å°ı
    0.10
     ëĭ¤ë¥¸
    0.10
    Activations Density 0.174%

    No Known Activations