© 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. 34256
    Prev
    Next
    INDEX
    Explanations

    cute, precious, adorable descriptions

    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
    å¼Ģåĩº
    -0.10
    度è¿ĩ
    -0.09
    æĢ¥äºİ
    -0.09
     tape
    -0.09
    apos
    -0.09
    tape
    -0.08
    æºľ
    -0.08
    åĪĢ
    -0.08
    à¹Ģส
    -0.08
     biom
    -0.08
    POSITIVE LOGITS
    å´½
    0.11
     chubby
    0.11
     adorable
    0.10
    ä¸įèĤ¯
    0.09
    åı¯çĪ±
    0.09
    ipel
    0.09
    åķĨæľº
    0.09
     Rail
    0.09
     charming
    0.08
     rails
    0.08
    Activations Density 0.067%

    No Known Activations