© 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. 58943
    Prev
    Next
    INDEX
    Explanations

    make sure followed by pronoun or determiner

    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
    strup
    -0.10
    æĪijçĽ¸ä¿¡
    -0.09
     sorte
    -0.09
    å¸ĮæľĽéĢļè¿ĩ
    -0.09
    .PREFERRED
    -0.09
    è¥Ł
    -0.09
    ä½ķç§į
    -0.08
    æĪij个人
    -0.08
    级以ä¸Ĭ
    -0.08
    .compress
    -0.08
    POSITIVE LOGITS
    ties
    0.10
    ĩ
    0.09
    ëĿ¼ëıĦ
    0.09
    ëĮĢë¡ľ
    0.09
    iah
    0.09
    ÙĬت
    0.09
     rằng
    0.08
    ä¸Ģ件äºĭ
    0.08
    wards
    0.08
    orial
    0.08
    Activations Density 0.017%

    No Known Activations