© 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. 2777
    Prev
    Next
    INDEX
    Explanations

    pioneer or pioneering

    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
    -bodied
    -0.30
    dogs
    -0.22
    ting
    -0.21
    ness
    -0.20
    teil
    -0.20
    tier
    -0.20
    ted
    -0.20
    åĴª
    -0.19
    geber
    -0.19
    tant
    -0.19
    POSITIVE LOGITS
    èĢħ
    0.27
    æĢ§çļĦ
    0.25
    èĢħçļĦ
    0.25
     efforts
    0.23
    erness
    0.22
    arily
    0.22
    ä¹ĭä½ľ
    0.21
    ously
    0.21
    èĢħãģ®
    0.20
    ä¸İåıijå±ķ
    0.20
    Activations Density 0.005%

    No Known Activations