© 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. 14579
    Prev
    Next
    INDEX
    Explanations

    castration, spaying, intact, reproductive status

    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
    æįŁ
    -0.20
     res
    -0.19
    chten
    -0.19
    leh
    -0.18
     stuff
    -0.18
     co
    -0.18
    å¼ĢéŨ
    -0.18
    å¤©åºľ
    -0.18
    chter
    -0.18
    ç¾½
    -0.17
    POSITIVE LOGITS
    é»ı
    0.20
    thood
    0.20
    	TokenName
    0.20
    ç²ĺ
    0.19
    ˣ
    0.19
    ãģ¤ãģĦ
    0.19
    urgent
    0.18
    穸
    0.18
    é£İæļ´
    0.18
    ink
    0.18
    Activations Density 0.001%

    No Known Activations