© 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. 2513
    Prev
    Next
    INDEX
    Explanations

    numbers forming citations

    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
    èĥ½å¾ĹåĪ°
    -0.27
    tips
    -0.24
    XR
    -0.24
    acre
    -0.23
    -transition
    -0.23
    æ©Ľ
    -0.21
    Surname
    -0.21
    ateg
    -0.21
    åıĪèĥ½
    -0.21
    Swipe
    -0.21
    POSITIVE LOGITS
     Blacks
    0.23
     (
    0.21
     Cou
    0.20
    éĨ®
    0.20
    Editors
    0.20
     Smash
    0.20
    âĺ°
    0.20
    ä¸įçŁ¥
    0.20
    inee
    0.20
     whites
    0.19
    Activations Density 0.074%

    No Known Activations