© 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. 36080
    Prev
    Next
    INDEX
    Explanations

    ownership and community

    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
    å¾·æĭī
    -0.09
    tings
    -0.09
     mileage
    -0.09
    çģ«åĬĽ
    -0.08
    å½°
    -0.08
    å°ļ
    -0.08
    渺
    -0.08
    å²³
    -0.08
     eth
    -0.08
    adm
    -0.08
    POSITIVE LOGITS
     ownership
    0.15
     Ownership
    0.14
    责任æĦŁ
    0.13
    主人
    0.13
    责任å¿ĥ
    0.13
    æīĢæľīæĿĥ
    0.13
    Ownership
    0.12
    å½Ĵå±ŀ
    0.11
    主ä½ĵ责任
    0.11
    ownership
    0.10
    Activations Density 0.044%

    No Known Activations