© 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. 49217
    Prev
    Next
    INDEX
    Explanations

    decades (e.g. '70s, '80s, '90s, '00s, '10s, '50s, '938)

    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
    ainment
    -0.11
    天é¹ħ
    -0.09
    éĬ®
    -0.09
    èĪĮ头
    -0.09
    oop
    -0.09
    Localization
    -0.08
    æĹĸ
    -0.08
    ⣵
    -0.08
    angler
    -0.08
    oure
    -0.08
    POSITIVE LOGITS
    SZ
    0.09
    å¯Ł
    0.08
    ูà¹Ī
    0.08
    äºĭåĦ¿
    0.08
    å½¢åĬ¿
    0.08
    èĢ³
    0.08
    èĨĿ
    0.08
     Spi
    0.08
    åħ«å¹´
    0.08
    è®©ä½ł
    0.08
    Activations Density 0.027%

    No Known Activations