© 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. 28058
    Prev
    Next
    INDEX
    Explanations

    law and order

    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
    ivity
    -0.13
    TING
    -0.12
    ยว
    -0.10
    SSION
    -0.10
    zelf
    -0.09
    ãģĦãģĨ
    -0.09
    åıijå±ķçIJĨ念
    -0.09
    ibil
    -0.09
    LOAT
    -0.09
    ogh
    -0.09
    POSITIVE LOGITS
    fully
    0.14
    lessly
    0.13
    yer
    0.13
    yers
    0.13
    ically
    0.13
    rence
    0.12
    breaker
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    vere
    0.10
    sons
    0.10
    Activations Density 0.039%

    No Known Activations