© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20311
    Prev
    Next
    INDEX
    Explanations

    Carolyn or yn names

    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
    eros
    -0.10
    æľīæĿ¡ä»¶çļĦ
    -0.10
    oret
    -0.10
    çļ¿
    -0.09
    inel
    -0.09
    ãi
    -0.09
    (?:
    -0.08
     Rosenberg
    -0.08
    eren
    -0.08
     exact
    -0.08
    POSITIVE LOGITS
    nya
    0.12
    shire
    0.12
    ne
    0.12
    soever
    0.11
    shaw
    0.11
    ed
    0.11
    ns
    0.10
    ss
    0.10
    ssa
    0.10
    ski
    0.10
    Activations Density 0.019%

    No Known Activations