© 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. 48234
    Prev
    Next
    INDEX
    Explanations

    integral and definite integral calculation

    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
    aring
    -0.11
    ãĤ¤
    -0.10
    _OPER
    -0.09
    ç»ı纬
    -0.09
    äºĶåĽĽ
    -0.08
    eline
    -0.08
    wal
    -0.08
    ÙĦاÙĦ
    -0.08
    Tac
    -0.08
    æĸĻ
    -0.08
    POSITIVE LOGITS
    积åĪĨ
    0.14
     integr
    0.10
     sum
    0.10
    èĩ§
    0.10
    âĪ«
    0.10
    sum
    0.10
    zech
    0.09
    éĽĨæĪIJ
    0.09
     Nab
    0.09
    åĮĻ
    0.09
    Activations Density 0.287%

    No Known Activations