© 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. 2040
    Prev
    Next
    INDEX
    Explanations

    men and boys

    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
    lic
    -0.25
    å¾®
    -0.25
    å¡«
    -0.24
    gregate
    -0.23
     airst
    -0.23
    毫
    -0.23
    çĽĬ
    -0.21
    çĹķ
    -0.21
     builtin
    -0.21
    cone
    -0.21
    POSITIVE LOGITS
    åĴĮ个人
    0.40
    åĴĮ
    0.34
     and
    0.33
    ãĢģ
    0.31
    åĴĮæĶ¯æĮģ
    0.30
     or
    0.29
     vÃł
    0.29
    ãĤĦ
    0.29
     vs
    0.28
    à¹ģละ
    0.28
    Activations Density 0.695%

    No Known Activations