© 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. 19235
    Prev
    Next
    INDEX
    Explanations

    open source software

    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
    irst
    -0.09
    綾
    -0.09
     mec
    -0.09
    æĶ¹éĿ©å¼ĢæĶ¾
    -0.08
    _STRUCTURE
    -0.08
    缩
    -0.08
    åı°ä¸Ĭ
    -0.08
    ìĨį
    -0.08
    _DRV
    -0.08
    嵩
    -0.08
    POSITIVE LOGITS
     Pron
    0.11
    åºĩ
    0.08
    ä¹ī
    0.08
    åij¨åĪĬ
    0.08
    æ¶ħ
    0.08
    éĿ¢åŃĶ
    0.08
     porte
    0.08
    èĮĹ
    0.08
    ctor
    0.08
    æĬĽå¼ĥ
    0.08
    Activations Density 0.209%

    No Known Activations