© 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. 33140
    Prev
    Next
    INDEX
    Explanations

    pave set, Sterling Silver, hand stamped necklace

    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
    ialis
    -0.09
    è¯Ŀ说
    -0.08
    ä¼IJ
    -0.08
     cord
    -0.08
    pv
    -0.08
    rick
    -0.08
    paired
    -0.07
    åij³
    -0.07
    endale
    -0.07
     seams
    -0.07
    POSITIVE LOGITS
     Ñĩел
    0.10
    ải
    0.10
    'gc
    0.09
    PLUS
    0.09
    å¿ĥæĥħ
    0.09
    ]=]
    0.08
    èĢĮæĪIJ
    0.08
     ÑĦин
    0.08
    à¸ģรรม
    0.08
    )null
    0.08
    Activations Density 0.009%

    No Known Activations