© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 37
    Prev
    Next
    INDEX
    Explanations

    drownings and rescue

    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
     Cabinets
    -0.31
    åıĹè´¿
    -0.26
    marshal
    -0.26
     publishers
    -0.25
    è´¿
    -0.25
     cabinet
    -0.24
     assass
    -0.24
     Armor
    -0.24
    æ©±æŁľ
    -0.23
     catalogs
    -0.23
    POSITIVE LOGITS
    æķijåĬ©
    0.49
    æķijæı´
    0.46
    èĩªæķij
    0.45
    çĻ»å±±
    0.42
    æ°´åŁŁ
    0.42
    æ°´ä¸Ĭ
    0.41
    æķij
    0.40
    æIJľæķij
    0.40
    æ¼Ĥæµģ
    0.40
     rescue
    0.38
    Activations Density 0.035%

    No Known Activations