© 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. 33545
    Prev
    Next
    INDEX
    Explanations

    beer and brewing enthusiasts

    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
     Chanel
    -0.09
    æŀģ
    -0.08
    YPE
    -0.08
     Chop
    -0.08
    íĤ¹
    -0.08
    çĻ½èıľ
    -0.08
    èĭĹ
    -0.08
    çıłå®Ŀ
    -0.08
    PIO
    -0.08
    .har
    -0.08
    POSITIVE LOGITS
    åķ¤éħĴ
    0.13
    éħ¿éĢł
    0.13
    éħ¿éħĴ
    0.12
    åķ¤
    0.11
     beer
    0.11
    çĵ¶åŃIJ
    0.11
     Brewers
    0.10
    å¼ĢéŨ
    0.10
    åĹľ
    0.10
    éħĴä¸ļ
    0.10
    Activations Density 0.099%

    No Known Activations