© 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. 2239
    Prev
    Next
    INDEX
    Explanations

    against

    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
     interchange
    -0.27
     Lessons
    -0.27
     Gespr
    -0.26
    è¡Ģ液
    -0.25
    æݢ访
    -0.24
    itung
    -0.23
     interceptions
    -0.22
    åIJ¬è§ģ
    -0.22
    reece
    -0.22
    åĩ»æĿĢ
    -0.22
    POSITIVE LOGITS
     entrenched
    0.32
    强大çļĦ
    0.28
     backdrop
    0.26
    åIJĮæł·æĺ¯
    0.26
    çªģå¦Ĥåħ¶
    0.25
    åIJĮæŶ
    0.25
    龸
    0.25
     onslaught
    0.25
     overwhelming
    0.25
     formidable
    0.25
    Activations Density 0.105%

    No Known Activations