© 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. 1624
    Prev
    Next
    INDEX
    Explanations

    not ... pattern

    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
     zwar
    -0.33
    èĻ½
    -0.31
    èĻ½çĦ¶
    -0.31
    èĻ½çĦ¶æĺ¯
    -0.30
     Already
    -0.28
    ä¸įä»ħè¦ģ
    -0.27
    éĽĸ
    -0.27
    ARIABLE
    -0.24
    ä½Ĩæĺ¯åľ¨
    -0.23
    èĻ½è¯´
    -0.23
    POSITIVE LOGITS
    æĬĬå®ĥ
    0.29
    为ä¹ĭ
    0.27
     equally
    0.27
     corresponding
    0.26
    为人
    0.25
    åĢŁæѤ
    0.24
     afterward
    0.24
     thereafter
    0.24
    缸åºĶçļĦ
    0.24
    ä¸Ŀ毫
    0.24
    Activations Density 0.159%

    No Known Activations