© 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. 23749
    Prev
    Next
    INDEX
    Explanations

    continuing, caring, pushing, playing

    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
    ucher
    -0.09
    å«ģ
    -0.09
    ĮĢ
    -0.09
    讨
    -0.08
    ä¼ĹæīĢ
    -0.08
    çĽ²çĽ®
    -0.08
    æ·¬
    -0.08
    绣çŃ¹æİ¨è¿Ľ
    -0.08
     амеÑĢикан
    -0.08
    洪水
    -0.08
    POSITIVE LOGITS
    æľªæĿ¥åıijå±ķ
    0.11
    åħ±åIJĮåıijå±ķ
    0.10
    æĺİ天
    0.10
    æľīæĽ´å¤ļçļĦ
    0.09
    acam
    0.09
    rita
    0.09
    åĨįè§ģ
    0.09
    è¶ĬæĿ¥è¶Ĭ
    0.09
     hopefully
    0.08
    _ios
    0.08
    Activations Density 0.007%

    No Known Activations