© 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. 35283
    Prev
    Next
    INDEX
    Explanations

    jdialog, jpanel, jframe, jtabbedpane, jumbotron

    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
     ÑĦак
    -0.08
    enny
    -0.08
    _HEAD
    -0.08
     Abel
    -0.08
    iri
    -0.08
    sil
    -0.08
    NameValuePair
    -0.08
     parach
    -0.08
    人工
    -0.08
    æIJºå¸¦
    -0.07
    POSITIVE LOGITS
    æĭĽåķĨ
    0.09
    å¸ĥå±Ģ
    0.09
    richt
    0.09
    èľĹ
    0.09
    çªĹ
    0.09
    ç»Ħ件
    0.09
    屯
    0.08
    .DockStyle
    0.08
    容纳
    0.08
    çļĦæĥħæĦŁ
    0.08
    Activations Density 0.950%

    No Known Activations