© 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. 14899
    Prev
    Next
    INDEX
    Explanations

    negative experiences or difficulties

    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
    utf
    -0.23
    éĢīå®ļ
    -0.20
    å¥ijåIJĪ
    -0.19
     давно
    -0.19
     ÑģегоднÑı
    -0.19
    EG
    -0.19
    ä¹ĭæīĢ以
    -0.19
    aton
    -0.19
    emp
    -0.19
     mant
    -0.19
    POSITIVE LOGITS
    æĢİä¹ĪåĬŀ
    0.29
    è¿Ļéĥ¨åĪĨ
    0.27
    ä¸įåħį
    0.25
    严éĩįå½±åĵį
    0.24
    è¿Ļç§įæĥħåĨµ
    0.23
    æĹłè¾ľ
    0.23
    å½±åĵį
    0.23
    åºĶåıĬæŶ
    0.23
    ä¸Ģ个éĹ®é¢ĺ
    0.22
    loo
    0.22
    Activations Density 0.096%

    No Known Activations