© 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. 12388
    Prev
    Next
    INDEX
    Explanations

    Fields like description, subtitle, message

    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
    æĹ¶å¸¸
    -0.23
    specifier
    -0.20
     Moose
    -0.19
    é«ĺæłĩåĩĨ
    -0.19
    åıijæī¬
    -0.18
    å¯ĩ
    -0.18
    icus
    -0.18
    æ´¸
    -0.17
    ortho
    -0.17
     topping
    -0.17
    POSITIVE LOGITS
    åIJ«
    0.27
    åħ¶ä¸Ńæľī
    0.23
    年产
    0.21
    产
    0.20
    èIJ½
    0.20
     Resolver
    0.20
    æııè¿°
    0.20
    æģ¯
    0.20
    çĶŁäº§åĴĮ
    0.19
    .cljs
    0.18
    Activations Density 0.196%

    No Known Activations