© 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. 21543
    Prev
    Next
    INDEX
    Explanations

    substantial quantity

    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
    tures
    -0.09
    roc
    -0.09
    logged
    -0.08
    eler
    -0.08
    æ¿Ģæĥħ
    -0.08
    ãģ¾ãģķ
    -0.08
    ä¸ĢåıĮ
    -0.08
    ën
    -0.08
    eters
    -0.08
    å´Ĩ
    -0.08
    POSITIVE LOGITS
    ment
    0.14
    ity
    0.14
    -bodied
    0.14
    mente
    0.11
    ively
    0.11
    ties
    0.10
    unts
    0.10
    į
    0.10
    ly
    0.10
    ITY
    0.09
    Activations Density 0.017%

    No Known Activations