© 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. 2347
    Prev
    Next
    INDEX
    Explanations

    Associated Press

    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
    å¾Ĺèµ·
    -0.27
     Ñģебе
    -0.23
    /remove
    -0.22
    åĴĮæĶ¯æĮģ
    -0.22
    asant
    -0.22
    ucceeded
    -0.22
    aju
    -0.21
     подаÑĢ
    -0.21
    å¾Ĺä½ı
    -0.21
    çī¹å®ļ
    -0.21
    POSITIVE LOGITS
     dispatch
    0.25
     reporter
    0.24
     Intl
    0.24
    ../../
    0.24
     journalists
    0.24
    æĸ°éĹ»
    0.23
    æĬ¥çº¸
    0.23
     newspaper
    0.23
     newspapers
    0.23
    åĵĪå°Ķ
    0.22
    Activations Density 0.010%

    No Known Activations