© 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. 49877
    Prev
    Next
    INDEX
    Explanations

    will be informed or receive

    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
    为空
    -0.11
    ä¸ĩåIJį
    -0.09
    bsub
    -0.09
    æħİ
    -0.09
    åĮħ
    -0.08
     полÑĮз
    -0.08
    çļĸ
    -0.08
    åıĪè¦ģ
    -0.08
    ä¸įè¦ģåĨį
    -0.08
    ibr
    -0.08
    POSITIVE LOGITS
    éĢļçŁ¥
    0.15
    åijĬè¯īä½ł
    0.14
    åıijå¸ĥåħ¬åijĬ
    0.13
    åħ¬åijĬ
    0.12
     notified
    0.12
    åijĬçŁ¥
    0.11
    ä¼ļåľ¨
    0.11
    åijĬè¯ī
    0.11
    éĢļæĬ¥
    0.10
    åijĬè¯ī大家
    0.10
    Activations Density 0.055%

    No Known Activations