© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36833
    Prev
    Next
    INDEX
    Explanations

    cannabis and marijuana legalization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åĨĽåĽ¢
    -0.10
    ä¸Ģéģį
    -0.10
    èĥĸåŃIJ
    -0.09
    çļ±çº¹
    -0.08
    åħ¸èĮĥ
    -0.08
    fuse
    -0.08
    æŃ£éĿ¢
    -0.08
    Tiny
    -0.08
    éļ¾å¾Ĺ
    -0.08
    åŃ£
    -0.08
    POSITIVE LOGITS
     screens
    0.10
    æĥ¯
    0.09
     trimmed
    0.09
     bầu
    0.09
    IntPtr
    0.09
    èĬ¥
    0.09
    æĥħä¾£
    0.09
    crypto
    0.08
    cobra
    0.08
    Parms
    0.08
    Activations Density 0.162%

    No Known Activations