© 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. 12502
    Prev
    Next
    INDEX
    Explanations

    men's and masculine items

    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
    ç¼ļ
    -0.21
    ié
    -0.19
    æŁĶ
    -0.19
    èĬ±å¼Ģ
    -0.19
    [][
    -0.18
    copyright
    -0.18
    æŁĶåĴĮ
    -0.18
    ://%
    -0.18
    è¡ĮåĬ¨è®¡åĪĴ
    -0.18
    红æĹĹ
    -0.18
    POSITIVE LOGITS
    çĶ·
    0.30
     male
    0.28
    çĶ·æĢ§
    0.28
    çĶ·åŃIJ
    0.27
    å¸ħæ°Ķ
    0.26
    çĶ·å£«
    0.26
     males
    0.24
     Male
    0.24
    娶
    0.24
    çĶ·äºº
    0.23
    Activations Density 0.195%

    No Known Activations