© 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. 1099
    Prev
    Next
    INDEX
    Explanations

    prior 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
    é¦ĸåħĪè¦ģ
    -0.24
    åı¦
    -0.24
    another
    -0.23
     Kron
    -0.22
    either
    -0.22
    æĺŁçº§
    -0.21
    Extern
    -0.21
    å°¤åħ¶æĺ¯åľ¨
    -0.21
    é¦ĸåħĪ
    -0.21
    /gpl
    -0.21
    POSITIVE LOGITS
    è¿Ļä¸ĢåĪĩ
    0.47
    è¿ĻçĤ¹
    0.44
    è¿Ļä¸ĢçĤ¹
    0.44
    è¿ĻäºĽ
    0.44
     this
    0.43
    è¿Ļä¸Ģ
    0.40
     these
    0.39
    è¿Ļæī¹
    0.36
    è¿Ļ个
    0.36
    è¿Ļæł·çļĦ
    0.36
    Activations Density 0.108%

    No Known Activations