© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2141
    Prev
    Next
    INDEX
    Explanations

    Danger, connecting, anniversary

    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
     furthermore
    -0.27
    就好åĥı
    -0.26
    æīĢ以ä»ĸ
    -0.26
    æīĢæīĢ
    -0.25
    CONDITION
    -0.25
    METHOD
    -0.24
    ç»ı纪人
    -0.23
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.23
    åĽłä¸ºä»ĸ
    -0.23
    å°±å¦ĤåIJĮ
    -0.23
    POSITIVE LOGITS
     reconsider
    0.27
     Beyond
    0.26
     unlikely
    0.26
     geopol
    0.26
     myths
    0.26
    —and
    0.26
     unequal
    0.25
    为ä½ķ
    0.25
     forgotten
    0.25
     lost
    0.25
    Activations Density 0.201%

    No Known Activations