© 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. 23609
    Prev
    Next
    INDEX
    Explanations

    evaluative 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
    éŃĤ
    -0.10
    åĪ»
    -0.09
    æijĨæĶ¾
    -0.09
    æ±Ŀ
    -0.09
    æģ°
    -0.09
    éĿ¢å¯¹éĿ¢
    -0.08
    éķĸ
    -0.08
    çŀħ
    -0.08
    漫
    -0.08
    åĻ¨æĿIJ
    -0.08
    POSITIVE LOGITS
    åı¯ä¿¡
    0.12
    æģ³
    0.09
    说æľį
    0.09
    丰满
    0.09
    Conversion
    0.09
    amma
    0.09
     Conversion
    0.09
    åħ±èµ¢
    0.09
    å®Įæķ´çļĦ
    0.09
     compelling
    0.09
    Activations Density 0.047%

    No Known Activations