© 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. 1189
    Prev
    Next
    INDEX
    Explanations

    personal access, Matlab, labor, TCP, soul, directly, components, services

    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æŀģæĢ§
    -0.25
     upbeat
    -0.23
    .sl
    -0.22
    梳
    -0.22
    saldo
    -0.22
    è¸Ĭè·ĥ
    -0.21
    å¿ħä¸įåı¯å°ij
    -0.21
    积æŀģä½ľçĶ¨
    -0.21
    å¢ŀæĶ¶
    -0.21
    veau
    -0.21
    POSITIVE LOGITS
    ä¹Łæ²¡æľī
    0.29
    ä¹ŁæĹłæ³ķ
    0.25
    çĻ¾ç§ij
    0.25
    pond
    0.25
    ä»»ä½ķ
    0.24
    ä¹Łä¸įçŁ¥éģĵ
    0.23
    ä¹Łä¸įåı¯èĥ½
    0.23
    ä½łè¯´
    0.23
    æľīä»»ä½ķ
    0.23
    鸾
    0.23
    Activations Density 0.015%

    No Known Activations