© 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. 1094
    Prev
    Next
    INDEX
    Explanations

    women, gas, females, android, liver, body

    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
    infra
    -0.24
    ĵį
    -0.23
    enne
    -0.22
    mts
    -0.22
    ZERO
    -0.22
    迦
    -0.22
     기íĥĢ
    -0.21
    /exp
    -0.21
    /class
    -0.21
     fitness
    -0.21
    POSITIVE LOGITS
     counterpart
    0.36
    åIJĮæł·
    0.34
    ä¹ŁåIJĮæł·
    0.33
     counterparts
    0.32
     similarly
    0.28
    åIJĮ樣
    0.25
    对åºĶçļĦ
    0.25
     likewise
    0.25
    çļĦè¯Ŀé¢ĺ
    0.24
    ä¸ĭåįķ
    0.24
    Activations Density 0.260%

    No Known Activations