© 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. 12512
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    äºĭå®ľ
    -0.26
    åĬ¼
    -0.19
    ä½ķå¤Ħ
    -0.18
    æ´ĭæ´ĭ
    -0.18
    ฯ
    -0.18
    ãģĦãģ§
    -0.17
    äºĮåŃĹ
    -0.17
    éļ¹
    -0.17
    æŁIJäºĽ
    -0.17
    æ½®
    -0.17
    POSITIVE LOGITS
    太ä¹ħ
    0.18
    exus
    0.18
    /be
    0.18
    _Command
    0.18
    undy
    0.17
     teil
    0.17
    nier
    0.17
     Lebanese
    0.17
    utt
    0.17
    åĿĬ
    0.17
    Activations Density 0.070%

    No Known Activations