© 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. 11326
    Prev
    Next
    INDEX
    Explanations

    charity: water projects for children

    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
    榷
    -0.24
    å¹²äºĭåĪĽä¸ļ
    -0.21
    åij¨åĪĬ
    -0.20
    西çĵľ
    -0.20
    ä¸įè§ģ
    -0.19
    è¨ĩ
    -0.19
    æĶ¹éĿ©åĪĽæĸ°
    -0.19
    åºĶä»ĺ
    -0.19
    æĸ¯åŁº
    -0.19
    æ¾İæ¹ĥæĸ°éĹ»
    -0.19
    POSITIVE LOGITS
     NYC
    0.22
    æįIJèµł
    0.21
     projectName
    0.21
     project
    0.20
    _QUAL
    0.20
    	project
    0.20
    å°ij女
    0.20
    èĥĦ
    0.20
    éĿĴå°ijå¹´
    0.19
    YE
    0.19
    Activations Density 0.048%

    No Known Activations