© 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. 26517
    Prev
    Next
    INDEX
    Explanations

    gambling, privacy, ID, score, practice

    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
    eder
    -0.08
    éĽĦåİļ
    -0.08
    _neighbors
    -0.08
    å®ĺ
    -0.08
    ä¿IJ
    -0.08
     preventative
    -0.08
     furnishings
    -0.07
    /etc
    -0.07
     pictured
    -0.07
    ä¿®
    -0.07
    POSITIVE LOGITS
    åį°åº¦
    0.11
     lakh
    0.10
     India
    0.10
    India
    0.10
     Gad
    0.10
    apur
    0.09
    âĤ¹
    0.09
     erst
    0.09
     till
    0.09
     Chennai
    0.09
    Activations Density 4.372%

    No Known Activations