© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 344
    Prev
    Next
    INDEX
    Explanations

    If possible

    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
     apparently
    -0.24
    BEL
    -0.22
    è¾±
    -0.22
     bied
    -0.22
     Bel
    -0.22
    æľ¬è´¨ä¸Ĭ
    -0.21
    Bel
    -0.21
    åı·ç§°
    -0.21
    tons
    -0.21
     wonder
    -0.21
    POSITIVE LOGITS
    å°½éĩı
    0.51
    å°½åı¯èĥ½
    0.42
     preferably
    0.35
    åģļåĪ°
    0.35
    ä¸įè¦ģ太
    0.34
    å°½æĹ©
    0.33
    æľĢ好æĺ¯
    0.31
    尽快
    0.29
    prefer
    0.29
     ideally
    0.28
    Activations Density 0.067%

    No Known Activations