© 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. 2721
    Prev
    Next
    INDEX
    Explanations

    contracts and purchases

    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
    è§Ħå¾ĭ
    -0.27
    åĽŃ
    -0.26
    æ¯ı个人
    -0.25
    è¿IJè¡Į
    -0.23
    éĥ½æľīèĩªå·±
    -0.23
    æ²»çIJĨ
    -0.23
    æ¯ı个人çļĦ
    -0.23
    _svc
    -0.22
     educated
    -0.22
    è¢«åĽ°
    -0.22
    POSITIVE LOGITS
     shipments
    0.28
    æĢ»é¢Ŀ
    0.28
    ecast
    0.28
     reaff
    0.28
    åħ±è®¡
    0.27
    为ä¸ŃåĽ½
    0.27
    æĢ»éĩı
    0.27
    确认
    0.25
     confirmed
    0.25
    ounder
    0.25
    Activations Density 0.015%

    No Known Activations