© 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. 5459
    Prev
    Next
    INDEX
    Explanations

    placing something

    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
    erot
    -0.11
    ä¸įçŁ¥ä¸įè§ī
    -0.10
    éļį
    -0.10
    èį¯ä¸ļ
    -0.10
    ç¼ĺåĪĨ
    -0.10
    ambi
    -0.10
    amba
    -0.09
    åıij表äºĨ
    -0.09
    以人为
    -0.09
    延伸
    -0.09
    POSITIVE LOGITS
    åľ¨ä¸Ģèµ·
    0.09
    åľ¨ä¸Ģ个
    0.09
    tin
    0.08
     bow
    0.08
    èĤ¢ä½ĵ
    0.07
    INF
    0.07
    åħ¥
    0.07
    à¦ĩ
    0.07
    缼
    0.07
    ä¸įåĪ©äºİ
    0.07
    Activations Density 0.015%

    No Known Activations