© 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. 57330
    Prev
    Next
    INDEX
    Explanations

    common development or law

    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
    没èĥ½
    -0.09
    åºĬä¸Ĭ
    -0.09
    åIJĮåŁİ
    -0.08
    ting
    -0.08
    èĻ±
    -0.08
    دÙĩ
    -0.08
    è¦ģéĹ»
    -0.08
    inverse
    -0.08
    åī§
    -0.08
    å§Ŀ
    -0.08
    POSITIVE LOGITS
    wealth
    0.19
    /shared
    0.11
    ality
    0.11
    -sama
    0.11
     Belgi
    0.10
    /Common
    0.10
    大ä¼Ĺ
    0.10
    esto
    0.10
    est
    0.09
    esa
    0.09
    Activations Density 0.048%

    No Known Activations