© 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. 62427
    Prev
    Next
    INDEX
    Explanations

    retailer actions

    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
    ãĤ£
    -0.10
    æł·çļĦ
    -0.10
     bald
    -0.10
    holes
    -0.09
    alty
    -0.09
    ãģĹãģ¾ãģĦ
    -0.09
    allet
    -0.09
    ÑĮ
    -0.09
    ä½°
    -0.09
    lessly
    -0.09
    POSITIVE LOGITS
    å¼ĢæĿ¥
    0.13
    巨头
    0.09
    tro
    0.09
    athe
    0.09
    еÑģÑĤв
    0.08
    夥
    0.08
    å¼Ħ
    0.08
    å¿ĥè¡Ģ管
    0.08
    æѤåĪ»
    0.08
    YPES
    0.08
    Activations Density 0.008%

    No Known Activations