© 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. 2230
    Prev
    Next
    INDEX
    Explanations

    actions or states

    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
     Redistributions
    -0.28
    ä¸įä½ı
    -0.26
    åģ¶
    -0.26
     lắm
    -0.25
    åģ¶çĦ¶
    -0.24
    æĬĸ
    -0.23
    ä¸įäºĨ
    -0.23
    æĿĤè´¨
    -0.23
    åģļä¸įåĪ°
    -0.23
     tires
    -0.22
    POSITIVE LOGITS
    ä¸ºæľŁ
    0.28
    份
    0.25
    ä»İäºĭ
    0.24
    .bc
    0.23
     weekly
    0.23
    è¿Ļ份
    0.23
    äºĨä¸Ģç³»åĪĹ
    0.23
    åľ¨å½ĵåľ°
    0.22
    ovel
    0.22
    approximately
    0.22
    Activations Density 0.495%

    No Known Activations