© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1360
    Prev
    Next
    INDEX
    Explanations

    due to limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     Cause
    -0.28
    å°±å¤Ł
    -0.26
    就好äºĨ
    -0.26
     Bound
    -0.24
    å°±å¤ŁäºĨ
    -0.24
     cause
    -0.24
     via
    -0.23
    æĪĸå¤ļ
    -0.23
     Organ
    -0.22
     Ways
    -0.22
    POSITIVE LOGITS
    缺ä¹ı
    0.34
     lack
    0.34
    大éĩıçļĦ
    0.29
    ä¼ĹæīĢåij¨çŁ¥
    0.29
     inability
    0.28
    çªģå¦Ĥåħ¶
    0.28
     limitations
    0.28
    çī¹æ®ĬçļĦ
    0.28
    çĸ«æĥħå½±åĵį
    0.28
    è¾ĥé«ĺçļĦ
    0.27
    Activations Density 0.126%

    No Known Activations