© 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. 1107
    Prev
    Next
    INDEX
    Explanations

    sports team locations or names

    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
    erial
    -0.26
    ä»Ĭ天æĪij们
    -0.25
    éħ£
    -0.24
    ä½ľåĵģåĨħ容
    -0.23
    aho
    -0.22
    å¹´èĩ³
    -0.22
    atches
    -0.22
    (loop
    -0.21
    ä¸įæĸŃåĪĽæĸ°
    -0.21
    éĵĹ
    -0.21
    POSITIVE LOGITS
     offer
    0.30
     already
    0.28
    æĽ´éĢĤåIJĪ
    0.28
    amba
    0.28
    éĢĤåIJĪ
    0.27
     candidacy
    0.27
    offer
    0.26
    çĶļèĩ³æĺ¯
    0.26
     accepting
    0.26
     offering
    0.26
    Activations Density 0.063%

    No Known Activations