© 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. 12027
    Prev
    Next
    INDEX
    Explanations

    handjob

    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
    æĺ¯å¯¹
    -0.22
    人å±ħ
    -0.21
     ÐIJлекÑģан
    -0.21
    æľīæĦı
    -0.20
    å±ħ
    -0.20
     à¹Ģมษ
    -0.20
     outside
    -0.19
    为åħ¶
    -0.19
    urga
    -0.19
     per
    -0.19
    POSITIVE LOGITS
    åĤķ
    0.21
    æ¬
    0.21
    éľĩèį¡
    0.21
    å¦Ĥæŀľçݩ家
    0.19
    ãİ¥
    0.19
    æľªç»ıæİĪæĿĥ
    0.18
    çİĭçīĮ
    0.18
    ä¸ĥæĺŁ
    0.18
     handjob
    0.18
    į°
    0.18
    Activations Density 0.039%

    No Known Activations