© 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. 57162
    Prev
    Next
    INDEX
    Explanations

    would have

    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
    æ¶Ĥ
    -0.09
    ä¸įçĪ±
    -0.09
    ç´¯äºĨ
    -0.09
    梳çIJĨ
    -0.08
    åŀĽ
    -0.08
    ä¸Ģèµ·åİ»
    -0.08
     ÐļÑĥ
    -0.08
    åĭĥ
    -0.08
    ody
    -0.08
    Jet
    -0.08
    POSITIVE LOGITS
    妪
    0.10
     걸
    0.09
    leen
    0.09
    anel
    0.09
    å·¥ä¼ļ
    0.09
    èıľ
    0.08
    opsy
    0.08
    .cgi
    0.08
     AUX
    0.08
    ewis
    0.08
    Activations Density 0.029%

    No Known Activations