© 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. 2462
    Prev
    Next
    INDEX
    Explanations

    amphetamine and meth use

    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
    ç»ŀ
    -0.24
    éĤ£ä»½
    -0.23
    åĩłå®¶
    -0.23
    ÅĪ
    -0.23
     Ham
    -0.21
    å¾Ĺä½ı
    -0.21
     plant
    -0.21
    .getConnection
    -0.21
     ham
    -0.20
    åIJĦ家
    -0.20
    POSITIVE LOGITS
    nation
    0.23
    downloads
    0.23
    mania
    0.23
    åĽ½éģĵ
    0.22
    aco
    0.21
     prefect
    0.21
    zan
    0.21
    æ§İ
    0.21
    idious
    0.20
    California
    0.20
    Activations Density 0.009%

    No Known Activations