© 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. 62104
    Prev
    Next
    INDEX
    Explanations

    enrichment analysis

    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
    UnderTest
    -0.12
    åĮħ袱
    -0.09
    /people
    -0.09
    ÑģÑĤвеннÑĭе
    -0.09
    ÙĦØ©
    -0.09
    /or
    -0.09
    ÙĦÙĩ
    -0.09
    orgen
    -0.08
    isi
    -0.08
    indy
    -0.08
    POSITIVE LOGITS
    ening
    0.11
    ãĥ£
    0.09
    壮大
    0.09
     tá»ij
    0.09
    ç¨ĭ度
    0.09
    es
    0.08
    æīĢåľ¨
    0.08
    ä¸ĭä¸Ģ代
    0.08
    (mapping
    0.08
    /disable
    0.08
    Activations Density 0.009%

    No Known Activations