© 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. 39057
    Prev
    Next
    INDEX
    Explanations

    what followed by something

    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
    beck
    -0.10
    å¾Ĵå¼Ł
    -0.09
    èĭķ
    -0.09
    ool
    -0.08
    æ·±çŁ¥
    -0.08
    綦
    -0.08
    åĨħç§ij
    -0.08
    uer
    -0.08
    ä¸Ģ次
    -0.08
    ä»Ķ
    -0.08
    POSITIVE LOGITS
    è¦ģ好好
    0.10
    Jar
    0.10
     Disclaimer
    0.09
    è´¯
    0.09
    åĽŀäºĭ
    0.09
    åıijçĶŁäºĨ
    0.09
     Maher
    0.09
    зд
    0.09
     tá»ĵn
    0.09
    çªĦ
    0.08
    Activations Density 0.032%

    No Known Activations