© 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. 12114
    Prev
    Next
    INDEX
    Explanations

    click, clip, latch, snap, coupling, release

    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
    沫
    -0.21
    注è§Ĩ
    -0.18
    obot
    -0.18
    绿水
    -0.18
    æĬĹè®®
    -0.18
    èµ°å»Ĭ
    -0.18
    å¯Ĥå¯ŀ
    -0.18
    æݨéĶĢ
    -0.17
    æĥ³æĥ³
    -0.17
    èģĶè°Ĭ
    -0.17
    POSITIVE LOGITS
    æľºåĪ¶
    0.26
    æī£
    0.23
     mechanism
    0.21
    çĶ·å¥³
    0.20
    åİŁçIJĨ
    0.19
    æīĵå¼Ģ
    0.18
    ä¼ļåijĺ
    0.18
    ç®Ģ便
    0.18
    /connection
    0.18
    éŨ
    0.18
    Activations Density 0.044%

    No Known Activations