© 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. 31410
    Prev
    Next
    INDEX
    Explanations

    Law, sea, or right angles

    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
    xit
    -0.10
    æīĵåĩ»
    -0.10
     tek
    -0.09
    LEM
    -0.09
    级åĪ«çļĦ
    -0.08
    StackSize
    -0.08
    åİĭæĬij
    -0.08
    esto
    -0.08
    öst
    -0.08
    .future
    -0.08
    POSITIVE LOGITS
    åģľæĶ¾
    0.09
    gee
    0.09
    åĴĮå°ļ
    0.08
    å¤ļä½Ļ
    0.08
    åģľå·¥
    0.08
    ä¸į太好
    0.08
    åĿĿ
    0.08
    ä»Ģä¹Īä¸ľè¥¿
    0.08
    fer
    0.08
    梵
    0.08
    Activations Density 0.049%

    No Known Activations