© 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. 27760
    Prev
    Next
    INDEX
    Explanations

    bankruptcy, agreement, court

    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
    åħij
    -0.09
    çķĮçļĦ
    -0.08
    å¸ĥå°Ķ
    -0.08
     Cran
    -0.08
    çĸ«
    -0.08
    aux
    -0.08
    ä¹ĭ称
    -0.08
    æľ¬å±Ĭ
    -0.08
    rench
    -0.08
    åıijåĩº
    -0.08
    POSITIVE LOGITS
    orra
    0.10
     forb
    0.09
    ioc
    0.09
    åĨ·åĨ»
    0.09
    úa
    0.09
    ç²ij
    0.09
    æĸ¹æ¡Ī
    0.09
    bite
    0.09
    IDD
    0.08
    ÑĮÑıн
    0.08
    Activations Density 0.032%

    No Known Activations