© 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. 12985
    Prev
    Next
    INDEX
    Explanations

    four* different* eggs* available* News* Q

    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
    æľ«
    -0.23
    å¨ī
    -0.22
    çĵĴ
    -0.22
    è¶ħåĩº
    -0.21
    çĻ¾åĪĨçĻ¾
    -0.20
    çĻ¾åĪĨä¹ĭ
    -0.20
    çļĦçŃĶæ¡Ī
    -0.20
    orf
    -0.20
    анÑģ
    -0.19
    çĻ½é©¬
    -0.19
    POSITIVE LOGITS
     Burr
    0.21
    æ¯ı个人éĥ½
    0.21
    è£ħæī®
    0.20
    æ·ĺ
    0.20
    quine
    0.20
    æ¯ı天éĥ½
    0.19
    æīĵæī®
    0.19
    æ¯ı次éĥ½
    0.19
    éĢļãĤĬ
    0.19
    agement
    0.19
    Activations Density 0.200%

    No Known Activations