© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37672
    Prev
    Next
    INDEX
    Explanations

    non-English characters and numbers

    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
    _vehicle
    -0.09
    _VC
    -0.09
    人人éĥ½
    -0.08
    äºĨèĩªå·±çļĦ
    -0.08
     Dud
    -0.08
    lint
    -0.08
    让èĩªå·±
    -0.08
    á»IJ
    -0.08
    _yes
    -0.08
    æĮº
    -0.08
    POSITIVE LOGITS
    ç½²
    0.10
    çıŃç»Ħ
    0.10
    ottage
    0.09
    Ùģع
    0.09
    ä»İä¸Ń
    0.09
    éĺĨ
    0.08
    SBATCH
    0.08
    æĹĹèĪ°
    0.08
    åħ¥åĽŃ
    0.08
    å´®
    0.08
    Activations Density 0.253%

    No Known Activations