© 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. 49954
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    çĶŁæŃ»
    -0.10
    æݥ触åĪ°
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.09
    åįļä¼ļ
    -0.09
    YST
    -0.08
    管çIJĨåĴĮ
    -0.08
    代çIJĨåķĨ
    -0.08
    ä¹ŁéĿŀ常
    -0.08
    äºĨä¸įå°ij
    -0.08
    è¿Ļå¥Ĺ
    -0.08
    POSITIVE LOGITS
    两èĢħ
    0.16
    äºĮèĢħ
    0.15
    以åıĬ
    0.12
    以åıĬåħ¶ä»ĸ
    0.11
    éĥ½ä¸įæĺ¯
    0.10
    çļĨ
    0.10
    åIJĦæľī
    0.10
    åĨįåĬłä¸Ĭ
    0.10
    以æѤ
    0.10
    交ç»ĩ
    0.09
    Activations Density 0.408%

    No Known Activations