© 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. 3780
    Prev
    Next
    INDEX
    Explanations

    analysis and modeling

    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
    èī¯
    -0.10
    èī¯å¥½
    -0.09
    èѦæĥķ
    -0.09
    .define
    -0.09
    aki
    -0.09
    NSE
    -0.08
    TAIL
    -0.08
    æĢħ
    -0.08
    èµ°è¿ĩ
    -0.08
    港èĤ¡
    -0.08
    POSITIVE LOGITS
    æµĭç®Ĺ
    0.15
    模æĭŁ
    0.12
    æķĪåºĶ
    0.10
    3
    0.10
    ä»¿çľŁ
    0.10
    è¯Ħä¼°
    0.10
    8
    0.09
     projections
    0.09
    åı¯è¡Į
    0.09
    æł¸ç®Ĺ
    0.09
    Activations Density 0.059%

    No Known Activations