© 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. 50152
    Prev
    Next
    INDEX
    Explanations

    get the most out of

    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
    RTL
    -0.10
    afil
    -0.10
    æľīäºĽ
    -0.09
    溲
    -0.09
     sper
    -0.09
    ier
    -0.08
    æł¸å®ŀ
    -0.08
    iting
    -0.08
    ål
    -0.08
    è§ī
    -0.08
    POSITIVE LOGITS
    .reader
    0.10
    ä½ĵéªĮ
    0.09
    è·Łå¥¹
    0.09
    åIJĮåŁİ
    0.09
    大èĩªçĦ¶
    0.09
     conspic
    0.08
     Dyn
    0.08
    cant
    0.08
    anth
    0.08
     Clem
    0.08
    Activations Density 0.013%

    No Known Activations