© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2344
    Prev
    Next
    INDEX
    Explanations

    low fat content

    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
     privately
    -0.23
    cause
    -0.23
    å¼Ģå±Ģ
    -0.23
    ä¸Ģåı¥
    -0.23
    åĮłå¿ĥ
    -0.23
    å¤Ļ
    -0.22
     gated
    -0.22
    çĶ¨è½¦
    -0.22
    ä¸Ģä¸ĸ
    -0.22
    facet
    -0.21
    POSITIVE LOGITS
    èĦĤèĤª
    0.28
    éĢŁ
    0.28
     skim
    0.27
    -fat
    0.26
     Indexed
    0.24
     ÑģодеÑĢж
    0.24
    bai
    0.23
    /non
    0.23
     fat
    0.23
    åIJ«éĩı
    0.23
    Activations Density 0.007%

    No Known Activations