© 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. 2138
    Prev
    Next
    INDEX
    Explanations

    committees and boards

    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
    å¹ķ
    -0.12
    åİ¿åħ¬å®īå±Ģ
    -0.10
    æIJŀ
    -0.10
    æĮĤ
    -0.09
    åºľ
    -0.09
    å¯ĵ
    -0.09
    åħ¬åĬ¡åijĺ
    -0.09
    æµģ失
    -0.09
    lico
    -0.09
    .lu
    -0.09
    POSITIVE LOGITS
    å§Ķåijĺä¼ļ
    0.12
     committees
    0.11
     committee
    0.11
    å·¥ä½ľç»Ħ
    0.10
    å§Ķåijĺ
    0.10
    å§Ķä¼ļ
    0.09
    çģ«çĦ°
    0.09
    é¢Ĩ导å°ıç»Ħ
    0.09
     board
    0.09
    å¥Ī
    0.09
    Activations Density 0.082%

    No Known Activations