© 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. 1544
    Prev
    Next
    INDEX
    Explanations

    hyperbaric oxygen and diving

    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
    è¾Ĺ
    -0.26
     Cricket
    -0.26
     drought
    -0.25
    ä¹±
    -0.25
     CONTRIBUTORS
    -0.23
    åĪ¤åĨ³
    -0.23
    grab
    -0.23
    æĬĵ
    -0.23
    [assembly
    -0.22
     pedido
    -0.22
    POSITIVE LOGITS
     underwater
    0.41
    æ°§æ°Ķ
    0.40
    æ½ľæ°´
    0.35
     oxygen
    0.34
     safely
    0.34
    æ°§
    0.33
    æİ¢éĻ©
    0.31
    èĪ±
    0.31
    omedical
    0.29
     underground
    0.28
    Activations Density 0.031%

    No Known Activations