© 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. 894
    Prev
    Next
    INDEX
    Explanations

    number one singles

    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
    ä¸Ģ楼
    -0.25
    ä¸Ģçķª
    -0.24
     jog
    -0.22
    èıģ
    -0.22
    odd
    -0.22
    éĴ°
    -0.21
    ä¼į
    -0.21
     polite
    -0.21
    æĹłåĬĽ
    -0.21
    enumerate
    -0.21
    POSITIVE LOGITS
    -rated
    0.24
    è¯Ŀ
    0.22
    ologie
    0.22
    sWith
    0.21
    bery
    0.21
     breadth
    0.21
     rated
    0.21
    ROID
    0.21
    çĿ«
    0.20
    èĤ¯
    0.20
    Activations Density 0.012%

    No Known Activations