© 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. 1120
    Prev
    Next
    INDEX
    Explanations

    you are welcome

    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
    [++
    -0.24
    artz
    -0.23
    ething
    -0.23
    ierz
    -0.22
    çļĦ人æĿ¥è¯´
    -0.22
     stemmed
    -0.22
    BitFields
    -0.21
    Fmt
    -0.21
    .VERSION
    -0.21
    çļĦæĹ¥åŃIJéĩĮ
    -0.21
    POSITIVE LOGITS
    æīĢå±ŀ
    0.30
    å¦Ĥæŀľæĺ¯
    0.30
    æīĢåľ¨
    0.28
    åħ¬ç¤º
    0.25
     candidate
    0.25
    æĪĸå¤ļ
    0.25
    æīĢåľ¨çļĦ
    0.24
    Interested
    0.24
    èģĶç½ij
    0.23
    è¦ģä¹Ī
    0.22
    Activations Density 0.118%

    No Known Activations