© 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. 840
    Prev
    Next
    INDEX
    Explanations

    Posted by, Posted by Author

    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
    ascade
    -0.28
    æ¸ħåįİ
    -0.25
    -dist
    -0.23
     pedest
    -0.23
    ä¸Ģ大æī¹
    -0.22
    çļĦæ°Ķæģ¯
    -0.22
    çļĦéģĵè·¯
    -0.22
    çļĦè¯Ńè¨Ģ
    -0.22
    æ¸ħåįİ大åѦ
    -0.22
    _ped
    -0.22
    POSITIVE LOGITS
    eldon
    0.29
    æ´º
    0.25
     Gang
    0.25
    reply
    0.25
     Reply
    0.24
     gang
    0.24
    è·Ľ
    0.23
    æĬĺåıł
    0.22
     alph
    0.22
     Replies
    0.21
    Activations Density 0.003%

    No Known Activations