© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37310
    Prev
    Next
    INDEX
    Explanations

    conviction for charge or crime

    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
     cont
    -0.09
    ãģ«åĩº
    -0.08
    ç»ı常ä¼ļ
    -0.08
    åħ¨å®¶
    -0.08
     trib
    -0.08
    ouver
    -0.08
    oks
    -0.08
    åijĺ
    -0.08
    patches
    -0.08
    OF
    -0.07
    POSITIVE LOGITS
    zelf
    0.10
    rif
    0.10
    bow
    0.10
    леж
    0.10
    еж
    0.10
    ->$
    0.09
    æĮ½
    0.09
     ден
    0.09
    FINE
    0.09
    身影
    0.09
    Activations Density 0.005%

    No Known Activations