© 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. 1843
    Prev
    Next
    INDEX
    Explanations

    slipping or flowing

    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
    积æ·Ģ
    -0.28
    è¿Ļ次
    -0.25
     privat
    -0.24
    身å¿ĥ
    -0.24
     civil
    -0.23
    cab
    -0.23
    æ°ijäºĭ
    -0.23
     Richard
    -0.23
    ideo
    -0.23
     Content
    -0.22
    POSITIVE LOGITS
    wick
    0.28
    对æīĭ
    0.27
    éĻ¤éĿŀ
    0.27
    稳å®ļæĢ§
    0.27
     loose
    0.26
    Yaw
    0.25
    éĺ²æŃ¢
    0.24
    è°ĥçļ®
    0.24
    wort
    0.24
     tendencies
    0.24
    Activations Density 0.082%

    No Known Activations