© 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. 2444
    Prev
    Next
    INDEX
    Explanations

    Indian film actors and places

    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
    .lua
    -0.28
     Monad
    -0.26
     Lisp
    -0.26
     ORD
    -0.26
     <*
    -0.25
    å´Ĥ
    -0.25
    屿
    -0.25
    elves
    -0.25
     Tasmania
    -0.24
    æĤīå°¼
    -0.24
    POSITIVE LOGITS
    è¹ħ
    0.32
    æ±Ī
    0.30
    åľIJ
    0.30
    åĻĩ
    0.30
     Bollywood
    0.29
     Rajasthan
    0.29
    磹
    0.29
    à¤ľ
    0.28
    åīħ
    0.28
     प
    0.28
    Activations Density 0.155%

    No Known Activations