© 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. 14904
    Prev
    Next
    INDEX
    Explanations

    prefix + suffix

    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
    çĶŁäº§åĴĮ
    -0.22
    ä¼ģä¸ļåĴĮ
    -0.21
    çIJĨ解åĴĮ
    -0.20
    æľĢåĪĿ
    -0.19
    ä¸ĢåĪĻ
    -0.18
    æĹ¢
    -0.18
     Princip
    -0.18
    è½»è½»åľ°
    -0.18
    æŶéĹ´åĴĮ
    -0.18
    æĹ¢åı¯ä»¥
    -0.18
    POSITIVE LOGITS
    /or
    0.35
    åħ¶å®ĥ
    0.29
    /etc
    0.27
    /OR
    0.27
    phans
    0.26
    acles
    0.24
     other
    0.24
     ÐIJлекÑģан
    0.23
    ign
    0.22
    other
    0.22
    Activations Density 0.067%

    No Known Activations