© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12435
    Prev
    Next
    INDEX
    Explanations

    cannabis and marijuana

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    溺
    -0.20
     gsl
    -0.19
    泪
    -0.19
    æѦåĬŁ
    -0.18
    çģ¾éļ¾
    -0.18
    çļ®éĿ©
    -0.18
    igne
    -0.18
    éħ±æ²¹
    -0.18
    ign
    -0.18
    <dyn
    -0.18
    POSITIVE LOGITS
     Marijuana
    0.28
     marijuana
    0.27
     cannabis
    0.26
     Cannabis
    0.24
    åIJĪæ³ķ
    0.21
    æĪĴ
    0.20
    类产åĵģ
    0.20
    .Restrict
    0.20
    cbd
    0.19
    ç¦ģ
    0.19
    Activations Density 0.041%

    No Known Activations