© 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. 57654
    Prev
    Next
    INDEX
    Explanations

    time periods and stages

    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¸ŃéĢĶ
    -0.09
    åĬ©éķ¿
    -0.09
    åĬ¡å®ŀ
    -0.09
    以为
    -0.09
    è½´
    -0.09
    æľ¬è½®
    -0.09
    ç²ī
    -0.08
    åIJįå½ķ
    -0.08
    ä¸įä½Ĩ
    -0.08
    ubby
    -0.08
    POSITIVE LOGITS
    ä¹ĭéĻħ
    0.10
    ä¹İ
    0.09
    çıŃ
    0.09
    åĨķ
    0.09
    ibble
    0.09
    ality
    0.08
    appa
    0.08
    欤
    0.08
     disposition
    0.08
    åĬŁå¾·
    0.08
    Activations Density 0.080%

    No Known Activations