© 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. 1453
    Prev
    Next
    INDEX
    Explanations

    -ic, -ical, -logy, -ally

    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
    .x
    -0.22
    ness
    -0.21
     PowerPoint
    -0.21
    orte
    -0.21
    ?p
    -0.21
     fleets
    -0.21
    ish
    -0.20
    åIJĦèĩªçļĦ
    -0.20
    uke
    -0.20
    ãģ£ãģ½
    -0.20
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.47
    åĴĮæĬĢæľ¯
    0.45
    æĦıä¹īä¸Ĭ
    0.38
    -economic
    0.38
    æĦıä¹īä¸ĬçļĦ
    0.36
    -wise
    0.34
    /met
    0.34
    /social
    0.32
    /pol
    0.30
    /method
    0.30
    Activations Density 0.546%

    No Known Activations