© 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. 11041
    Prev
    Next
    INDEX
    Explanations

    building a web application

    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
    æѧ
    -0.09
    åij¼
    -0.09
    ادر
    -0.08
    ç£ķ
    -0.08
    第ä¸ĢåIJį
    -0.08
    qb
    -0.08
     вообÑīе
    -0.08
    çĶ·äºº
    -0.08
    Behind
    -0.08
    æ¯ķ
    -0.08
    POSITIVE LOGITS
    è£ĺ
    0.11
    é¹¾
    0.10
    åľ¨å½ĵåľ°
    0.10
    è¯Ŀè¯Ń
    0.09
    妮
    0.09
    æ¦Ħ
    0.09
    brick
    0.09
    好æľĭåıĭ
    0.09
    çĮ·
    0.09
    .tap
    0.09
    Activations Density 1.201%

    No Known Activations