© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13336
    Prev
    Next
    INDEX
    Explanations

    art and drawing activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     strapon
    -0.23
     shemale
    -0.22
     Curl
    -0.19
     lesbi
    -0.19
    ustum
    -0.19
    èĶij
    -0.19
    (Packet
    -0.19
     milfs
    -0.19
     QTableWidgetItem
    -0.19
     باÙĦت
    -0.18
    POSITIVE LOGITS
    åĪĽä½ľ
    0.29
    çĶ»çĶ»
    0.29
    ç»ĺçĶ»
    0.26
    å¹¼åĦ¿
    0.24
    ä½ľåĵģ
    0.24
    æ²¾
    0.24
    èīºæľ¯å®¶
    0.24
    åѦåīį
    0.23
    æ¶Ĥ
    0.23
    èĺ¸
    0.23
    Activations Density 0.010%

    No Known Activations