© 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. 2761
    Prev
    Next
    INDEX
    Explanations

    Windows and Android operating systems

    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
     gloss
    -0.26
     Ire
    -0.24
     Sands
    -0.24
     Aad
    -0.24
    å±Ĥå±Ĥ
    -0.23
     Watching
    -0.22
    å¿ĥçĸ¼
    -0.22
    Watching
    -0.22
    Boundary
    -0.22
    æ°Ķåij³
    -0.22
    POSITIVE LOGITS
    éĺµèIJ¥
    0.31
    antium
    0.26
    -powered
    0.25
    æĪĺçķ¥æĢ§
    0.25
    è´§
    0.25
    åIJĪä½ľ
    0.24
    çļĦæĪĺçķ¥
    0.24
    ustrial
    0.24
     gamb
    0.23
     alternatives
    0.23
    Activations Density 0.027%

    No Known Activations