© 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. 798
    Prev
    Next
    INDEX
    Explanations

    lead to

    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
    ä»Ĺ
    -0.24
    æŀ¶åŃIJ
    -0.24
    wu
    -0.23
    ç«ĭåľº
    -0.22
    istani
    -0.21
     stature
    -0.21
    teen
    -0.21
    ä½ıäºĨ
    -0.20
     guise
    -0.20
    èģĶç³»æĸ¹å¼ı
    -0.20
    POSITIVE LOGITS
    uce
    0.26
    çļĦç»ĵæŀľ
    0.26
    ä¸Ģç³»åĪĹ
    0.25
    äºĨä¸Ģç³»åĪĹ
    0.24
     outcomes
    0.23
    ings
    0.23
    ä¸Ģ个æĸ°çļĦ
    0.23
    丰ç¡ķ
    0.23
    çģŃ亡
    0.22
    å¾Ĺåĩº
    0.22
    Activations Density 0.040%

    No Known Activations