© 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. 18262
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases suggesting movement

    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
    æīįèĥ½å¤Ł
    -0.09
    æĶ
    -0.08
    åŃ
    -0.08
    ä¼łè¨Ģ
    -0.08
    éĢ¸
    -0.08
    pace
    -0.08
    ickets
    -0.08
    è¿ŀéĶģ
    -0.08
    alling
    -0.08
    çݩ家们
    -0.08
    POSITIVE LOGITS
    è®ĵä»ĸåĢij
    0.10
    让ä»ĸ们
    0.10
    ä»ĸèĩªå·±
    0.10
    带åĪ°
    0.10
    isu
    0.10
    æªĢ
    0.10
    èĥ³èĨĬ
    0.09
    è®ĵä»ĸ
    0.09
    alem
    0.09
    ä¸įèĩ³äºİ
    0.09
    Activations Density 0.115%

    No Known Activations