© 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. 2676
    Prev
    Next
    INDEX
    Explanations

    history of prohibition and alcohol

    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
     Performing
    -0.23
    ANDROID
    -0.23
     Flags
    -0.23
    BOR
    -0.23
    recur
    -0.22
     Fukushima
    -0.22
    Meg
    -0.22
    nze
    -0.22
     diverse
    -0.22
    gart
    -0.21
    POSITIVE LOGITS
    æ³ķè§Ħ
    0.35
    åºŁ
    0.35
    -era
    0.34
    æĹ¶æľŁçļĦ
    0.34
     prohibition
    0.33
     outlaw
    0.33
     Alcohol
    0.32
     enforcement
    0.32
     laws
    0.32
     booze
    0.31
    Activations Density 0.010%

    No Known Activations