© 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. 1993
    Prev
    Next
    INDEX
    Explanations

    surface of a

    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
    TestFixture
    -0.25
    笼
    -0.23
     cage
    -0.22
     fixation
    -0.22
    sat
    -0.22
     Cage
    -0.22
    ["+
    -0.22
    kü
    -0.22
     cages
    -0.22
    nı
    -0.21
    POSITIVE LOGITS
     Trick
    0.28
    ç»ĥä¹ł
    0.23
     Roz
    0.23
    ç·´
    0.22
    åı¤ä»Ĭ
    0.22
    ä¸ĢäºĮ
    0.22
     pov
    0.22
    ynam
    0.22
    çĨŁ
    0.22
    ogg
    0.21
    Activations Density 0.001%

    No Known Activations