© 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. 32349
    Prev
    Next
    INDEX
    Explanations

    nice followed by appreciative adjectives

    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
    设计çIJĨ念
    -0.10
    å¥Ħ
    -0.10
    æĢĿç´¢
    -0.09
    horn
    -0.09
    踯
    -0.09
    çIJĨ解åĴĮ
    -0.08
    æľīèī²
    -0.08
    æİĩ
    -0.08
    çļĤ
    -0.08
    еÑĢÑĮ
    -0.08
    POSITIVE LOGITS
    åı¯çĪ±çļĦ
    0.11
     lovely
    0.10
     wonderful
    0.10
     Ñĥдоб
    0.10
     nice
    0.10
     handy
    0.10
    iki
    0.09
    诱
    0.09
     little
    0.09
     Machinery
    0.09
    Activations Density 0.038%

    No Known Activations