© 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. 1185
    Prev
    Next
    INDEX
    Explanations

    addressing you or your

    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
    åIJĦåĽ½
    -0.28
    apo
    -0.26
    optional
    -0.24
    olib
    -0.24
    ä¸īä½įä¸Ģä½ĵ
    -0.24
    sm
    -0.23
    æľĢä½³
    -0.23
    section
    -0.23
    dest
    -0.23
    ä¸Ģ个个
    -0.23
    POSITIVE LOGITS
     presumably
    0.54
     likely
    0.44
     probably
    0.40
    ãģ¨ãģ®ãģĵãģ¨
    0.37
    ãģĬãģĿãĤīãģı
    0.34
    æĹ¢çĦ¶
    0.34
     possibly
    0.33
     your
    0.32
    æĤ¨çļĦ
    0.32
    æĥ³å¿ħ
    0.31
    Activations Density 0.192%

    No Known Activations