© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1082
    Prev
    Next
    INDEX
    Explanations

    sign language, single sign-on

    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
    èĴ¸æ±½
    -0.26
    åĩºåİĤ
    -0.23
     steam
    -0.22
    steam
    -0.22
    ä¾Ľæ°´
    -0.22
    ahead
    -0.21
    çıŃ
    -0.21
    noon
    -0.21
    elin
    -0.21
    grades
    -0.21
    POSITIVE LOGITS
     Mellon
    0.25
    IRM
    0.23
     TLC
    0.23
     kata
    0.23
     lenders
    0.22
     lady
    0.22
    ç»İ
    0.22
    æ©IJ
    0.22
     Tuple
    0.21
    shire
    0.21
    Activations Density 0.002%

    No Known Activations