© 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. 153
    Prev
    Next
    INDEX
    Explanations

    names and companies

    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
     irres
    -0.24
    çĵ¶
    -0.23
    REAK
    -0.23
     alone
    -0.22
    è¿Ļå¥Ĺ
    -0.22
    è¿°
    -0.22
     gras
    -0.21
    artner
    -0.21
    åıĻ
    -0.21
    宿
    -0.21
    POSITIVE LOGITS
    ä¹ĭ家
    0.26
     Household
    0.23
     Workplace
    0.23
     household
    0.22
    å¨Ī
    0.22
     Coding
    0.22
    æĪ·
    0.22
     Playground
    0.22
     SG
    0.22
     Helpful
    0.22
    Activations Density 0.026%

    No Known Activations