© 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. 2899
    Prev
    Next
    INDEX
    Explanations

    JavaScript DOM manipulation

    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
    .ascii
    -0.30
    åĪ¶
    -0.27
    .utf
    -0.25
    .mk
    -0.25
    åĪ¶åº¦
    -0.24
    OptionsResolver
    -0.24
    ä¼ī
    -0.24
    .atan
    -0.24
    adena
    -0.23
    .Produ
    -0.23
    POSITIVE LOGITS
     sibling
    0.33
    æīĢåľ¨çļĦ
    0.32
     children
    0.31
    appendChild
    0.30
     HTMLElement
    0.30
     container
    0.29
     element
    0.29
    åħĥç´ł
    0.28
    éļIJèĹı
    0.28
    HTMLElement
    0.28
    Activations Density 1.456%

    No Known Activations