© 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. 57400
    Prev
    Next
    INDEX
    Explanations

    team names

    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
    åĴ¬
    -0.10
    otto
    -0.10
    让人们
    -0.10
    äºĨä»ĸçļĦ
    -0.09
    åķĥ
    -0.09
    âĺ°
    -0.09
    åģıåģı
    -0.09
    ivent
    -0.09
    SEG
    -0.09
    å±Ļ
    -0.09
    POSITIVE LOGITS
     Tar
    0.09
    à§İ
    0.08
    tar
    0.08
     mist
    0.08
    鸯
    0.08
    èĭĹ
    0.08
    upe
    0.07
    _round
    0.07
    0
    0.07
    è´¡
    0.07
    Activations Density 0.006%

    No Known Activations