© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10035
    Prev
    Next
    INDEX
    Explanations

    vehicle parked or resting

    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
     пÑĢÑı
    -0.10
    Jet
    -0.09
    è°Ł
    -0.09
     ürünü
    -0.09
    /packages
    -0.09
    è°³
    -0.09
    鼻åŃIJ
    -0.09
    riding
    -0.09
    æ¸ĶèĪ¹
    -0.09
     dog
    -0.09
    POSITIVE LOGITS
    驶
    0.11
    åģľæĶ¾
    0.11
    æĺ¯çĶ¨æĿ¥
    0.10
    éĵĥ
    0.10
    ä¸ĩè¾Ĩ
    0.09
    è¡Į驶
    0.09
    åĽĽä½į
    0.09
    夫
    0.09
    çīĮçħ§
    0.09
    fter
    0.09
    Activations Density 0.131%

    No Known Activations