© 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. 3742
    Prev
    Next
    INDEX
    Explanations

    decoration and decor

    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
    -0.12
    hood
    -0.10
    ynet
    -0.09
    eger
    -0.09
     nạn
    -0.09
    踪
    -0.09
    addle
    -0.09
    æŃ©
    -0.08
    croft
    -0.08
    æģ¯
    -0.08
    POSITIVE LOGITS
    ../../../
    0.11
    çĹ¢
    0.10
    ating
    0.09
    ally
    0.09
    ECT
    0.09
    herence
    0.09
    ipel
    0.09
    FileStream
    0.09
    .AR
    0.09
    ãĥŃãĥ¼ãĥ³
    0.08
    Activations Density 0.012%

    No Known Activations