© 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. 30412
    Prev
    Next
    INDEX
    Explanations

    wanting or intending something

    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
    FTA
    -0.08
    峡
    -0.08
    对æīĭ
    -0.08
    大大å°ı
    -0.08
    ä¼ļåIJĮ
    -0.08
    çľĭèµ·æĿ¥
    -0.07
    缮çļĦåľ¨äºİ
    -0.07
    以为
    -0.07
    ä¸Ģè·¯ä¸Ĭ
    -0.07
     popular
    -0.07
    POSITIVE LOGITS
     Rossi
    0.09
    &view
    0.09
    asti
    0.09
    åį«è§Ĩ
    0.09
    _placement
    0.08
    çĶ©
    0.08
    åĢ¦
    0.08
    зи
    0.08
    åįķ纯çļĦ
    0.08
    UEST
    0.08
    Activations Density 0.319%

    No Known Activations