© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 11632
    Prev
    Next
    INDEX
    Explanations

    "interact"

    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
    æŃ¤ç±»
    -0.09
    лей
    -0.09
    çĨĬ
    -0.09
    oral
    -0.08
    æīĢè°ĵ
    -0.08
     Mass
    -0.08
    åĽłæŀľ
    -0.08
    éķ°
    -0.08
    å¥ĩ迹
    -0.08
    åľ¨åĨħçļĦ
    -0.08
    POSITIVE LOGITS
    èĥĮä¸Ĭ
    0.11
    ä¸ĵä¸ļä»İäºĭ
    0.10
    æķ´é¡¿
    0.09
    åĽ½åľŁèµĦæºIJ
    0.09
    åīįä¸ĸ
    0.09
    alah
    0.09
    天èĬ±æĿ¿
    0.09
    伸åĩº
    0.09
    arf
    0.09
    çĩ®
    0.08
    Activations Density 0.049%

    No Known Activations