© 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. 48767
    Prev
    Next
    INDEX
    Explanations

    space agencies and nasa

    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
    åįıä¼ļä¼ļéķ¿
    -0.10
    ä¸Ģéģį
    -0.09
    便æ°ij
    -0.09
    交
    -0.09
    luet
    -0.09
    äºĤ
    -0.09
     pac
    -0.09
    èł²
    -0.09
    åĪĢ
    -0.08
    ç§ĺ书
    -0.08
    POSITIVE LOGITS
    èĪ±
    0.15
    èĪªå¤©
    0.15
    NASA
    0.14
    嫦
    0.13
    å®ĩ
    0.12
     NASA
    0.12
    é£ŀèĪ¹
    0.12
    ç§ijæĻ®
    0.12
     astronauts
    0.11
    åıijå°Ħ
    0.11
    Activations Density 0.241%

    No Known Activations