© 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. 18868
    Prev
    Next
    INDEX
    Explanations

    SYSTEM response

    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
    æĭĽ
    -0.10
    åı£è¢ĭ
    -0.09
    shoot
    -0.08
    uche
    -0.08
    éĽĨä¸Ń
    -0.08
    lost
    -0.08
    ulls
    -0.08
    è°ª
    -0.08
     union
    -0.08
    chrom
    -0.07
    POSITIVE LOGITS
    çŀª
    0.13
    ä¼ģä¸ļæıIJä¾Ľ
    0.11
    çļĦ产åĵģ
    0.10
    å®ļåĪ¶
    0.10
    å©¿
    0.10
     SOFTWARE
    0.10
    åĶ®
    0.10
    åİĤåķĨ
    0.10
    èĿī
    0.10
    软件
    0.10
    Activations Density 0.212%

    No Known Activations