© 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. 436
    Prev
    Next
    INDEX
    Explanations

    fracture, react

    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
    -0.25
     lẽ
    -0.22
    说æĺ¯
    -0.20
    Ñĩик
    -0.20
    metic
    -0.20
    æѤåĪ»
    -0.19
        ↵    ↵    ↵
    -0.19
    entifier
    -0.19
    ging
    -0.19
    icial
    -0.19
    POSITIVE LOGITS
    ively
    0.31
    ivity
    0.27
    ural
    0.26
    累累
    0.24
    ors
    0.24
    ive
    0.22
    IVITY
    0.22
    urus
    0.22
    ives
    0.21
    ible
    0.21
    Activations Density 0.222%

    No Known Activations