© 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. 26914
    Prev
    Next
    INDEX
    Explanations

    final goal or outcome

    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
    æ¯Ķäºļ
    -0.09
    çĢļ
    -0.08
    ä¸į足以
    -0.08
    è¿Ħä»Ĭ为æŃ¢
    -0.08
    ìŀĩ
    -0.08
    骢
    -0.08
    åı¯ä¿¡
    -0.08
    omat
    -0.08
    len
    -0.08
    å¤ļåIJĥ
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.12
    vely
    0.11
    ities
    0.11
    çĹĩ
    0.10
    mente
    0.10
    åķ¬
    0.10
    subpackage
    0.10
    gy
    0.09
    泡
    0.09
    getRepository
    0.09
    Activations Density 0.010%

    No Known Activations