© 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. 22082
    Prev
    Next
    INDEX
    Explanations

    funding and finance sources

    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
    亲æīĭ
    -0.10
    丫头
    -0.09
    rint
    -0.09
    ãĥijãĤ¹
    -0.09
    糧
    -0.09
    便æ°ij
    -0.08
    åijĬè¯ī大家
    -0.08
    èļ´
    -0.08
     Hood
    -0.08
    annot
    -0.08
    POSITIVE LOGITS
    èµŀåĬ©
    0.17
    èµĦåĬ©
    0.16
     funding
    0.16
    èµĦéĩij
    0.14
    ç»ıè´¹
    0.14
    åĪ°ä½į
    0.14
    æĶ¯æĮģ
    0.13
     Funding
    0.12
    _sources
    0.12
    æĦ¿æĦı
    0.11
    Activations Density 0.056%

    No Known Activations