© 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. 15106
    Prev
    Next
    INDEX
    Explanations

    importance or necessity

    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
    åı¯èĥ½æĢ§
    -0.20
    (zip
    -0.19
    åģļæ³ķ
    -0.19
    ä¸įäºĨ
    -0.19
    via
    -0.18
    anything
    -0.18
    æĥħåĨµ
    -0.18
    èī®
    -0.18
    åħ¬ä¸»
    -0.18
    æĿ¥çļĦ
    -0.18
    POSITIVE LOGITS
    åħ³éĶ®
    0.32
    éĿŀ常éĩįè¦ģ
    0.30
     crucial
    0.30
    çļĦåħ³éĶ®
    0.29
    éĩįè¦ģçļĦ
    0.28
    å¾Īéĩįè¦ģ
    0.27
    èĩ³åħ³éĩįè¦ģ
    0.27
     important
    0.26
     vital
    0.25
    åįģåĪĨéĩįè¦ģ
    0.25
    Activations Density 0.303%

    No Known Activations