© 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. 2548
    Prev
    Next
    INDEX
    Explanations

    codes and numbers

    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
    глÑıд
    -0.26
    edBy
    -0.23
    :///
    -0.23
    GLOBALS
    -0.22
    çľĭæĿ¥
    -0.22
     MILL
    -0.21
    æľĪ以æĿ¥
    -0.21
    issant
    -0.21
    Mill
    -0.21
    world
    -0.20
    POSITIVE LOGITS
    anner
    0.26
    mmas
    0.23
    åīįç½®
    0.22
    æĤ£
    0.22
    éĽĨ群
    0.22
    ÑĩÑĢежден
    0.21
    esters
    0.21
    åį±å®³
    0.21
     Condition
    0.21
    ANNER
    0.21
    Activations Density 0.047%

    No Known Activations