© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6466
    Prev
    Next
    INDEX
    Explanations

    buying gold, bitcoin, guns, or going off-grid

    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
    ç»ĩ
    -0.10
    (vo
    -0.10
    halt
    -0.09
    ç«¥è£ħ
    -0.09
    æĿĵ
    -0.09
    план
    -0.09
    ç³»
    -0.09
    åį¤
    -0.09
    æ±ŁåĮº
    -0.09
    æµħ
    -0.08
    POSITIVE LOGITS
    é»į
    0.10
    éĩijéĵ¶
    0.10
    è´µéĩijå±ŀ
    0.10
    åħ¸
    0.10
    屯
    0.09
    lok
    0.09
    åĤ¨èĵĦ
    0.08
    èµĦ产
    0.08
    åŃĺåĤ¨
    0.08
    æı¡
    0.08
    Activations Density 0.148%

    No Known Activations