© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15245
    Prev
    Next
    INDEX
    Explanations

    wait with bated breath

    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
    æĶ¾åĩº
    -0.24
    ç»
    -0.20
    æīģ
    -0.20
    éĤ£å°±æĺ¯
    -0.19
    ãĤĴè¦ĭãĤĭ
    -0.19
    åħ¬æŃ£
    -0.18
    igne
    -0.18
    æķ´ä½ĵ
    -0.17
    ä¸Ńå¿ĥåŁİåĮº
    -0.17
    å¿Ĵ
    -0.17
    POSITIVE LOGITS
     festive
    0.19
    ANE
    0.18
    èĤ¢
    0.18
    atism
    0.18
    åĴ«
    0.18
    对éĿ¢
    0.18
    ãģĦãģ£ãģŁ
    0.18
    æĩĭ
    0.18
     hakk
    0.18
    çĬĴ
    0.18
    Activations Density 0.002%

    No Known Activations