© 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. 55095
    Prev
    Next
    INDEX
    Explanations

    crystal structure

    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
    çĽĹ
    -0.10
    èIJ½
    -0.09
    åĬŀäºĭ
    -0.09
    åĪ°äºĨ
    -0.09
    满èĦ¸
    -0.09
     Vine
    -0.08
    è¿Ķ
    -0.08
    åĬŀçIJĨ
    -0.08
    enson
    -0.08
    弧
    -0.08
    POSITIVE LOGITS
    é«ĺä»·
    0.10
    éºŁ
    0.09
    æĻ¶ä½ĵ
    0.09
    è¿Ń
    0.09
    解æŀIJ
    0.09
    ocking
    0.08
    pite
    0.08
    æ¯į
    0.08
    裹
    0.08
     crystal
    0.08
    Activations Density 0.248%

    No Known Activations