© 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. 61616
    Prev
    Next
    INDEX
    Explanations

    lymphoma

    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
    æ¶ķ
    -0.09
    åľ¹
    -0.09
    jiang
    -0.09
    åĸĶ
    -0.08
    åľ°æĿ¿
    -0.08
     tin
    -0.08
    åħľ
    -0.08
    åĶ§
    -0.08
    amin
    -0.08
     Tin
    -0.08
    POSITIVE LOGITS
    cci
    0.10
    ä¸ŃåİŁ
    0.09
    ILA
    0.09
    åĩ»
    0.08
    è¦ģçŁ¥éģĵ
    0.08
    à¸ļาย
    0.08
    estre
    0.08
    樨
    0.08
    hora
    0.08
    ******/
    0.08
    Activations Density 0.006%

    No Known Activations