© 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. 57893
    Prev
    Next
    INDEX
    Explanations

    travel

    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
    å¹´æĬ¥
    -0.09
    è¾°
    -0.09
    çĭĻ
    -0.09
    æIJ¬è¿IJ
    -0.09
    æİĺ
    -0.08
    onna
    -0.08
    æľ´
    -0.08
    çıĪ
    -0.08
    æĪijæł¡
    -0.08
    ogh
    -0.08
    POSITIVE LOGITS
    abad
    0.08
    å§Ĭ妹
    0.08
     Unlock
    0.08
    bound
    0.08
    çĽ´è¾¾
    0.08
    éľĸ
    0.08
    åģı好
    0.08
     overnight
    0.08
    .preferences
    0.08
    çķĮ
    0.08
    Activations Density 0.122%

    No Known Activations