© 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. 37931
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases introducing context

    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
    ä¼ļéķ¿
    -0.10
    以èī²
    -0.09
    è¿ľæĸ¹
    -0.09
    addChild
    -0.09
    åħĢ
    -0.09
    å¢ĥ
    -0.08
    _FWD
    -0.08
    æĢħ
    -0.08
    acement
    -0.08
    ä¸ĸ人
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·æīįèĥ½
    0.12
    æĪijæīį
    0.11
    è¿Ļä¸ĢçĤ¹
    0.10
    /small
    0.10
    è¿ĻäºĽä¸ľè¥¿
    0.09
    è¿Ļ件äºĭ
    0.09
    è¿ĻäºĽ
    0.09
    _THIS
    0.09
    èĢĮéĿŀ
    0.09
    ãģĵãĤĮãĤīãģ®
    0.09
    Activations Density 0.049%

    No Known Activations