© 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. 3870
    Prev
    Next
    INDEX
    Explanations

    concise articulation

    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
     лÑĥÑĩ
    -0.09
    ниÑĩ
    -0.09
    rite
    -0.08
    ние
    -0.08
    noon
    -0.08
     Vig
    -0.08
     nh
    -0.08
     Ñģог
    -0.08
    æµĵ缩
    -0.08
    åŃĹä½ĵ
    -0.08
    POSITIVE LOGITS
    ä»ħ代表
    0.12
    بة
    0.10
    europ
    0.10
    ä»Ģä¹Īæĺ¯
    0.09
    acies
    0.09
    人士
    0.09
    ately
    0.09
    伶
    0.09
    é«ĺæķĪçļĦ
    0.09
    æľīåĬĽ
    0.09
    Activations Density 0.005%

    No Known Activations