© 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. 11207
    Prev
    Next
    INDEX
    Explanations

    adjusting or making changes

    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
    ä¸į解
    -0.09
    è¾Ļ
    -0.09
    åĮĸçŁ³
    -0.09
    cape
    -0.08
    JOB
    -0.08
    íĥĪ
    -0.08
    cheap
    -0.08
    arning
    -0.08
    ết
    -0.08
    å¥ij约
    -0.08
    POSITIVE LOGITS
    è°ĥæķ´
    0.12
    調æķ´
    0.11
     ajust
    0.09
    åģıå·®
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    abi
    0.09
     adjust
    0.09
    maal
    0.09
    .adjust
    0.09
    æĶ¾å®½
    0.09
    Activations Density 0.045%

    No Known Activations