© 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. 22233
    Prev
    Next
    INDEX
    Explanations

    start / began

    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
    å°Ĩ以
    -0.10
    åıijå±ķä¸Ń
    -0.09
    å¹½
    -0.09
     NG
    -0.08
     Strauss
    -0.08
    overe
    -0.08
    æł¹æºIJ
    -0.08
    Stra
    -0.08
    ä»ĭ
    -0.08
    åģļè¿ĩ
    -0.08
    POSITIVE LOGITS
    æĢ§å¼º
    0.10
    åĬ¨æijĩ
    0.09
    egl
    0.09
     Sears
    0.09
    аÑĤоÑĢ
    0.09
    holm
    0.08
     shar
    0.08
    åį´è¢«
    0.08
    嬷
    0.08
    èĺijèıĩ
    0.08
    Activations Density 0.011%

    No Known Activations