© 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. 49321
    Prev
    Next
    INDEX
    Explanations

    account for

    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
    æŃ¥
    -0.10
     previews
    -0.10
    zej
    -0.10
    alah
    -0.10
    ä¸įåı¯æĢĿ
    -0.09
    å¯ĦãģĽ
    -0.09
    ç½¢
    -0.09
    梵
    -0.09
    åĨħå¿ĥçļĦ
    -0.09
    ç¥ģ
    -0.09
    POSITIVE LOGITS
     accounted
    0.14
    è§ĴèIJ½
    0.09
    æ¶ĪèĢĹ
    0.09
    Account
    0.09
    é¾Ľ
    0.08
     Account
    0.08
    åĩºå¤Ħ
    0.08
     accountability
    0.08
     quota
    0.08
     commitments
    0.08
    Activations Density 0.081%

    No Known Activations