© 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. 19627
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "make", "know", "explore"

    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
    reek
    -0.09
    å«ĸ
    -0.09
    ä¸įäºĨ
    -0.09
    èŁł
    -0.08
    å¸ĿåĽ½
    -0.08
    åİĦ
    -0.08
    ogn
    -0.08
    éĿŀ常å¤ļçļĦ
    -0.08
     certainly
    -0.08
    åĵģä½į
    -0.08
    POSITIVE LOGITS
    ØŁ
    0.09
    读åIJİ
    0.09
    liced
    0.08
    åĩłå¼ł
    0.08
    ãģ§ãģĻãģĭ
    0.08
    kah
    0.08
     Tu
    0.08
    åŀ¦
    0.08
    åIJĹ
    0.08
    éĹ¾
    0.08
    Activations Density 0.031%

    No Known Activations