© 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. 33816
    Prev
    Next
    INDEX
    Explanations

    space mission or international project

    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
    æŀ³
    -0.09
    echa
    -0.09
    讼
    -0.09
    è¸Ĭ
    -0.08
    (cx
    -0.08
    æĩĭ
    -0.08
    ugu
    -0.08
    æģ¬
    -0.08
     Cas
    -0.08
    bib
    -0.08
    POSITIVE LOGITS
     missions
    0.12
     mission
    0.11
    _PRIORITY
    0.11
    æİ¢æµĭ
    0.11
    使åij½
    0.10
    å®ŀåľ°
    0.10
    éĩįçĤ¹é¡¹çĽ®
    0.10
    ä»»åij½
    0.09
     tong
    0.09
    æīĭæĮģ
    0.09
    Activations Density 0.085%

    No Known Activations