© 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. 15074
    Prev
    Next
    INDEX
    Explanations

    dropping out of school

    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
    èµį
    -0.22
    çĿ¡åīį
    -0.19
     duties
    -0.19
    éĺħ
    -0.19
    éĹº
    -0.19
    gp
    -0.18
    èī°å·¨
    -0.18
    ĥģ
    -0.18
    oring
    -0.18
    彤
    -0.18
    POSITIVE LOGITS
     school
    0.20
     dropout
    0.20
    æ³ĵ
    0.19
    å¤ĦåĪĨ
    0.19
    è¾į
    0.19
    èįī
    0.18
    èħĪ
    0.18
    Reality
    0.18
    rypton
    0.18
    ÑģÑĤи
    0.18
    Activations Density 0.006%

    No Known Activations