© 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. 1186
    Prev
    Next
    INDEX
    Explanations

    understanding what

    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
    åĬ¨åijĺ
    -0.24
    åIJİæĤĶ
    -0.24
    æĹ¥èµ·
    -0.23
    æľīåħ´è¶£
    -0.23
    èĩªæĦ¿
    -0.23
    æĶ¶çĽĬçİĩ
    -0.23
    éħ¬
    -0.22
     disfr
    -0.22
    .clock
    -0.22
    å¥ĸéĩij
    -0.22
    POSITIVE LOGITS
    客æĪ·éľĢæ±Ĥ
    0.36
    æ´ŀå¯Ł
    0.29
    ä½ĵè´´
    0.26
    _ctxt
    0.25
    æįķæįī
    0.24
     respect
    0.23
    æķıéĶIJ
    0.23
     understands
    0.23
    çIJĨ解
    0.22
    æĢ§åĴĮ
    0.22
    Activations Density 0.052%

    No Known Activations