© 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. 27313
    Prev
    Next
    INDEX
    Explanations

    professionals related to education

    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
    ãģ¬
    -0.10
    èĬľ
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    nob
    -0.09
    /or
    -0.09
    æ¹¾
    -0.09
    ä¸Ģ个éĩįè¦ģ
    -0.09
    mith
    -0.09
    ãĤĮ
    -0.08
    ench
    -0.08
    POSITIVE LOGITS
     вÑģего
    0.10
     tầm
    0.10
    инг
    0.09
    们
    0.09
    ssel
    0.09
    窿
    0.09
    IFI
    0.09
    zia
    0.09
    åIJĮäºĭ们
    0.09
    ree
    0.08
    Activations Density 0.023%

    No Known Activations