© 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. 327
    Prev
    Next
    INDEX
    Explanations

    search for

    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
     gonna
    -0.26
     hindsight
    -0.25
     regards
    -0.25
     striving
    -0.24
     chance
    -0.23
    _IOCTL
    -0.22
    achten
    -0.22
     gro
    -0.22
    ylene
    -0.22
     scrutiny
    -0.22
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.31
    å±ŀäºİèĩªå·±
    0.30
    éĢĤåIJĪèĩªå·±
    0.28
    缸åħ³ä¿¡æģ¯
    0.25
    ä¸ĭä¸Ģ个
    0.24
    /upload
    0.23
    ä¸Ģ个æĸ°çļĦ
    0.23
    /select
    0.23
    ä¸ĭä¸Ģ
    0.23
    /design
    0.23
    Activations Density 0.024%

    No Known Activations