© 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. 35394
    Prev
    Next
    INDEX
    Explanations

    parking and related issues

    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
    éĢłçº¸
    -0.09
    产åĵģè´¨éĩı
    -0.09
    侧éĩį
    -0.08
    èµĬ
    -0.08
     aud
    -0.08
     pur
    -0.08
    çĤķ
    -0.08
    åIJĬ
    -0.08
    aug
    -0.08
    宣
    -0.08
    POSITIVE LOGITS
    车ä½į
    0.16
    åģľè½¦ä½į
    0.15
     parking
    0.14
     Parking
    0.14
    åģľè½¦
    0.14
    åģľè½¦åľº
    0.14
    æ³Ĭ
    0.13
    åħħçĶµæ¡©
    0.13
    Parking
    0.12
    åģľæĶ¾
    0.11
    Activations Density 0.097%

    No Known Activations