© 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. 754
    Prev
    Next
    INDEX
    Explanations

    toxicological properties

    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
     pizza
    -0.30
    ä½įç½®
    -0.27
    çļĦä½įç½®
    -0.27
    å®īè£ħ
    -0.27
    æİ¥éĢģ
    -0.26
     locker
    -0.26
     pizzas
    -0.25
    åĮ¹éħį
    -0.25
     village
    -0.25
    æīĢåľ¨çļĦ
    -0.25
    POSITIVE LOGITS
    æ¯ĴæĢ§
    0.56
     toxicity
    0.54
    èĩ´çĻĮ
    0.44
    æ¯Ĵ
    0.44
     toxic
    0.43
     Toxic
    0.41
    æľī害
    0.40
     carcin
    0.40
    æľīæ¯Ĵ
    0.39
    åį±å®³
    0.38
    Activations Density 0.312%

    No Known Activations