© 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. 17625
    Prev
    Next
    INDEX
    Explanations

    mistakes, missed, poor

    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
    eut
    -0.09
    DDS
    -0.09
    ogue
    -0.09
    è¦ĨçĽĸçİĩ
    -0.09
    anic
    -0.09
     дело
    -0.09
    setStatus
    -0.08
    æľīçĽĬ
    -0.08
    åIJĪçIJĨ
    -0.08
    è¯ķè¯ķ
    -0.08
    POSITIVE LOGITS
    åı¯ä»¥è¯´æĺ¯
    0.11
    éħ¿
    0.09
    çĻ½çĻ½
    0.08
    ref
    0.08
    ç¼Ļ
    0.08
    é¾
    0.08
    éªĦåĤ²
    0.08
    undos
    0.08
    meld
    0.08
    çĶµåŃIJ产åĵģ
    0.08
    Activations Density 0.009%

    No Known Activations