© 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. 30478
    Prev
    Next
    INDEX
    Explanations

    multimedia recreation and tasks

    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
    æĤ»
    -0.10
    ä¸įç»ı
    -0.09
     Slip
    -0.09
    èŀ³
    -0.09
    åħ¨åĽ½åIJĦåľ°
    -0.09
    ç»Ĥ
    -0.09
    责任
    -0.09
    ç¥ĿæĦ¿
    -0.08
    俱
    -0.08
    丰åİļ
    -0.08
    POSITIVE LOGITS
    ocom
    0.10
    çĶľç¾İ
    0.09
    çľĭäºĨä¸Ģ
    0.09
    娱ä¹IJ
    0.09
    ¬
    0.09
    çľĭçĶµå½±
    0.09
    æ¶ĪèĢĹ
    0.09
    dra
    0.09
    ä¸Ĭç½ij
    0.09
     LAN
    0.08
    Activations Density 0.296%

    No Known Activations