© 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. 2883
    Prev
    Next
    INDEX
    Explanations

    causing an action or reaction

    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
    æ¯ıä¸Ģ
    -0.24
    ty
    -0.24
    bred
    -0.23
    å®ŀåĬĽ
    -0.23
    Ñģко
    -0.23
    ety
    -0.23
     thân
    -0.23
    缦
    -0.22
    weet
    -0.22
    她æĺ¯
    -0.22
    POSITIVE LOGITS
    ä¸Ģç³»åĪĹ
    0.36
    äºĨä¸Ģç³»åĪĹ
    0.36
    äºĨä¸Ģåľº
    0.29
    å¹¿æ³Ľåħ³æ³¨
    0.29
    è´¨çĸij
    0.29
    ä¸Ģåľº
    0.28
    ä¸Ģ个éĹ®é¢ĺ
    0.28
     nationwide
    0.28
    AMED
    0.25
    ç«ĭåį³
    0.24
    Activations Density 0.028%

    No Known Activations