© 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. 50721
    Prev
    Next
    INDEX
    Explanations

    air hanging or in the air

    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
    åħ¨æ°ij
    -0.08
    èĹı
    -0.08
    ç§Ģ
    -0.08
    橱
    -0.08
    èĦ±
    -0.08
    裾
    -0.08
    _modifier
    -0.08
    _Method
    -0.08
    DN
    -0.08
     Seah
    -0.08
    POSITIVE LOGITS
    空ä¸Ń
    0.18
    空æ°Ķ
    0.15
    空æ°Ķä¸Ń
    0.14
     воздÑĥÑħ
    0.12
    天空
    0.11
     air
    0.11
    æĬ½åıĸ
    0.10
    ä¸Ńç§ĭ
    0.10
    air
    0.09
    åĽĽæĸ¹
    0.09
    Activations Density 0.040%

    No Known Activations