© 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. 58409
    Prev
    Next
    INDEX
    Explanations

    prepositions of motion and direction

    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
    aye
    -0.09
    è¯Ŀ说
    -0.09
    æĹĹä¸ĭçļĦ
    -0.09
    æ°§
    -0.08
    feito
    -0.08
    åīĬ
    -0.08
    ç½ijæ°ij
    -0.08
    éĵł
    -0.08
    ç½²
    -0.08
    Ø´Ùĩ
    -0.08
    POSITIVE LOGITS
    个åĪ«
    0.09
    /questions
    0.09
    ä¸įçĶ±å¾Ĺ
    0.09
    hog
    0.08
    unge
    0.08
    æľīåĩłä¸ª
    0.08
    confidence
    0.08
    xing
    0.08
    ience
    0.08
    ä¹ĭä½ľ
    0.08
    Activations Density 0.270%

    No Known Activations