© 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. 3925
    Prev
    Next
    INDEX
    Explanations

    net combined with financial or scientific terms

    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
    hower
    -0.10
    éĢŀ
    -0.09
    scape
    -0.09
    enco
    -0.08
    âķ°
    -0.08
    èĥ¡åŃIJ
    -0.08
    ((&
    -0.08
    matchCondition
    -0.08
    fur
    -0.08
    èѦæĥķ
    -0.08
    POSITIVE LOGITS
    ãģĤãĤĮ
    0.11
    ting
    0.09
    erv
    0.09
    åĬĽéĩı
    0.09
    åī©
    0.08
    ep
    0.08
    /net
    0.08
    iy
    0.08
    lify
    0.08
    楼å±Ĥ
    0.08
    Activations Density 0.017%

    No Known Activations