© 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. 12559
    Prev
    Next
    INDEX
    Explanations

    months following wednesday

    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
    ivil
    -0.18
    eat
    -0.17
    (JNIEnv
    -0.17
    epar
    -0.17
     вÑĭпÑĥÑģ
    -0.17
    åĴĮæĬĢæľ¯
    -0.17
    OrFail
    -0.17
    åĴĮåľ°åĮº
    -0.17
    大声
    -0.17
    æŨ
    -0.17
    POSITIVE LOGITS
    åıĪ称
    0.20
    odon
    0.18
    åIJī祥
    0.18
    æįİ
    0.17
    åķĨæľº
    0.17
    åĽĽç§į
    0.17
    åĨ¤
    0.16
    nell
    0.16
    éĶ¦æłĩ
    0.16
    å¥ĭæĸĹ缮æłĩ
    0.16
    Activations Density 0.037%

    No Known Activations