© 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. 30326
    Prev
    Next
    INDEX
    Explanations

    Bedford and Bridgewater places

    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
    Rock
    -0.09
    ãģĹãĤĩãģĨ
    -0.08
    omo
    -0.08
    顶å±Ĥ设计
    -0.08
    ëıħ
    -0.08
    aka
    -0.08
    tern
    -0.08
     дог
    -0.08
    protobuf
    -0.08
     Christie
    -0.08
    POSITIVE LOGITS
    ÙĬات
    0.12
    geh
    0.10
    edly
    0.10
    cmc
    0.10
    ANEL
    0.10
    HEN
    0.09
    shire
    0.09
    ÑĤÑģÑı
    0.09
    æģĤ
    0.09
    GINE
    0.09
    Activations Density 0.005%

    No Known Activations