© 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. 813
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by main verbs

    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
     ÑĢейÑĤинг
    -0.24
    åij½
    -0.23
     Amen
    -0.23
    ä¸įå®Į
    -0.23
    -ajax
    -0.22
    ä¸Ģèµ·æĿ¥
    -0.22
    åįĬå°ıæŶ
    -0.21
    æĪij们ä¸Ģèµ·
    -0.21
    äºĶæĺŁ
    -0.21
    otty
    -0.21
    POSITIVE LOGITS
    _unique
    0.22
    åĽºåĮĸ
    0.22
    _DIP
    0.22
    äºĴ
    0.21
    èĩªæ²»
    0.21
     unique
    0.21
    æ³½è¿ŀ
    0.20
     equip
    0.20
    Aqu
    0.20
     Gaz
    0.20
    Activations Density 0.523%

    No Known Activations