© 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. 62118
    Prev
    Next
    INDEX
    Explanations

    compliant, under, approval, rating

    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
    cki
    -0.09
    avigator
    -0.08
    omp
    -0.08
    å¦ĤæľŁ
    -0.08
    ault
    -0.08
     Fres
    -0.08
    vice
    -0.08
    ç»ıèIJ¥æ´»åĬ¨
    -0.08
    æĪĸå°Ĩ
    -0.08
    Base
    -0.08
    POSITIVE LOGITS
    aar
    0.10
    ikt
    0.10
    认è¯ģ
    0.09
    é«ĺéĢŁ
    0.09
    IRA
    0.09
    å®īåħ¨æĢ§
    0.09
    符åIJĪ
    0.08
    มหา
    0.08
    æŀī
    0.08
    .handleChange
    0.08
    Activations Density 0.043%

    No Known Activations