© 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. 824
    Prev
    Next
    INDEX
    Explanations

    change-over

    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
     trì
    -0.26
    è¯ļ
    -0.25
    åħ±åIJĮåĬªåĬĽ
    -0.24
    ride
    -0.23
    è¿ĺæľª
    -0.23
    è°Ľ
    -0.23
    éĻī
    -0.23
    å®ŀéĻħä¸Ĭæĺ¯
    -0.23
    rait
    -0.21
    è°ģçŁ¥
    -0.21
    POSITIVE LOGITS
    æ·ĺæ±°
    0.32
     uninstall
    0.32
    ä¸įçķĻ
    0.32
    æ¸ħçIJĨ
    0.31
    .removeFrom
    0.31
    åį¸
    0.30
    æĢ¥éľĢ
    0.29
    å¤ļä½ĻçļĦ
    0.29
     deselect
    0.28
    éĢĢå½¹
    0.28
    Activations Density 0.222%

    No Known Activations