© 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. 2434
    Prev
    Next
    INDEX
    Explanations

    scores and numerical sequences

    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
     roma
    -0.25
    dings
    -0.24
    å¹´éĻIJ
    -0.23
    ä¸Ģéĥ¨
    -0.23
    忸
    -0.23
     Libre
    -0.23
    ç«Ļéķ¿
    -0.23
    _MALLOC
    -0.23
    ivant
    -0.22
    è¿Ļ个èģĮä¸ļ
    -0.22
    POSITIVE LOGITS
    åıįåĩ»
    0.28
     counter
    0.24
     essentially
    0.24
    tit
    0.24
     proceeding
    0.23
    ressive
    0.23
     retrieval
    0.23
     chain
    0.23
     penalty
    0.22
    æĿ¥èĩªäºİ
    0.22
    Activations Density 0.002%

    No Known Activations