© 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. 4949
    Prev
    Next
    INDEX
    Explanations

    self-driving vehicles

    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
    pun
    -0.09
    çª
    -0.09
    åIJĪçIJĨ
    -0.09
    æī©æķ£
    -0.08
    orna
    -0.08
     kênh
    -0.08
    /extensions
    -0.08
    åĽ½ç½ij
    -0.08
    èµı
    -0.08
    æľīåĬĽ
    -0.08
    POSITIVE LOGITS
    æĹłäºº
    0.16
    æĹłäººé©¾é©¶
    0.14
    èĩªåĬ¨é©¾é©¶
    0.12
    èĩªé©¾
    0.10
    驾驶
    0.10
     automat
    0.10
    åĩ¸
    0.09
     automát
    0.09
    automation
    0.09
     driving
    0.09
    Activations Density 0.090%

    No Known Activations