© 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. 62336
    Prev
    Next
    INDEX
    Explanations

    ruin and ruins

    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
    sis
    -0.10
    ivity
    -0.10
    à¹Į
    -0.09
    çĶ¨åĵģ
    -0.09
    REA
    -0.09
    ê°ģ
    -0.09
    æļĿ
    -0.09
     LGPL
    -0.09
     valida
    -0.08
    ern
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.11
    ously
    0.10
    ous
    0.10
    æ»ĵ
    0.09
    пиÑģ
    0.09
    ough
    0.09
    fully
    0.09
    ful
    0.09
    ï¸
    0.09
    amu
    0.09
    Activations Density 0.012%

    No Known Activations